llama-cpp-server/models-preset.ini

; Auto-generated llama.cpp models preset
; generated-at = 2026-07-06 15:00:32
; models-dir = E:\LMStudio\.lmstudio\models
; select = all
; profile = smart
; alias-style = section
; backup = none

version = 1

[HauhauCS/Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced-GGUF:Q4_K_P]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced-GGUF\Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced-Q4_K_P.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced-GGUF\mmproj-Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced-f16.gguf
alias = HauhauCS/Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced-GGUF:Q4_K_P
; ctx-size range = 512..262144; chosen = 43008
ctx-size = 43008
; n-gpu-layers range = 0..30; chosen = 30
n-gpu-layers = 30
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.7
top-k = 40
top-p = 0.95
min-p = 0.0
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true
; n-cpu-moe range = 0..30; chosen = 0
n-cpu-moe = 0

[HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF\Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF\mmproj-Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf
alias = HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 43008
ctx-size = 43008
; n-gpu-layers range = 0..40; chosen = 40
n-gpu-layers = 40
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.7
top-k = 40
top-p = 0.95
min-p = 0.0
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true
; n-cpu-moe range = 0..40; chosen = 0
n-cpu-moe = 0

[HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-GGUF\Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-GGUF\mmproj-Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf
alias = HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..32; chosen = 32
n-gpu-layers = 32
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF\Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-NoThink-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF\mmproj-Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf
alias = HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..32; chosen = 32
n-gpu-layers = 32
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-GGUF\Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-GGUF\mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf
alias = HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..32; chosen = 32
n-gpu-layers = 32
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF\Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-NoThink-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF\mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf
alias = HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..32; chosen = 32
n-gpu-layers = 32
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_P]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-GGUF\Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-GGUF\mmproj-Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-f16.gguf
alias = HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_P
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..64; chosen = 64
n-gpu-layers = 64
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Balanced-GGUF:Q4_K_P]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.6-27B-Uncensored-HauhauCS-Balanced-GGUF\Qwen3.6-27B-Uncensored-HauhauCS-Balanced-Q4_K_P.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.6-27B-Uncensored-HauhauCS-Balanced-GGUF\mmproj-Qwen3.6-27B-Uncensored-HauhauCS-Balanced-f16.gguf
alias = HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Balanced-GGUF:Q4_K_P
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..64; chosen = 64
n-gpu-layers = 64
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF\Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF\mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf
alias = HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 43008
ctx-size = 43008
; n-gpu-layers range = 0..40; chosen = 40
n-gpu-layers = 40
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.7
top-k = 40
top-p = 0.95
min-p = 0.0
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true
; n-cpu-moe range = 0..40; chosen = 0
n-cpu-moe = 0

[HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF\Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NoThink-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF\mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf
alias = HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NoThink-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 43008
ctx-size = 43008
; n-gpu-layers range = 0..40; chosen = 40
n-gpu-layers = 40
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.7
top-k = 40
top-p = 0.95
min-p = 0.0
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true
; n-cpu-moe range = 0..40; chosen = 0
n-cpu-moe = 0

[HauhauCS/Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\HauhauCS\Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-GGUF\Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf
alias = HauhauCS/Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 32768
ctx-size = 32768
; n-gpu-layers range = 0..36; chosen = 36
n-gpu-layers = 36
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[Tencent/HY-MT1.5-1.8B-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\Tencent\HY-MT1.5-1.8B-GGUF\HY-MT1.5-1.8B-Q4_K_M.gguf
alias = Tencent/HY-MT1.5-1.8B-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 32768
ctx-size = 32768
; n-gpu-layers range = 0..32; chosen = 32
n-gpu-layers = 32
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[ggml-org/Qwen3-ASR-1.7B-GGUF:Q8_0]
model = E:\LMStudio\.lmstudio\models\ggml-org\Qwen3-ASR-1.7B-GGUF\Qwen3-ASR-1.7B-Q8_0.gguf
mmproj = E:\LMStudio\.lmstudio\models\ggml-org\Qwen3-ASR-1.7B-GGUF\mmproj-Qwen3-ASR-1.7B-bf16.gguf
alias = ggml-org/Qwen3-ASR-1.7B-GGUF:Q8_0
; ctx-size range = 512..65536; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..28; chosen = 28
n-gpu-layers = 28
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[ggml-org/SmolVLM2-500M-Video-Instruct-GGUF:Q8_0]
model = E:\LMStudio\.lmstudio\models\ggml-org\SmolVLM2-500M-Video-Instruct-GGUF\SmolVLM2-500M-Video-Instruct-Q8_0.gguf
mmproj = E:\LMStudio\.lmstudio\models\ggml-org\SmolVLM2-500M-Video-Instruct-GGUF\mmproj-SmolVLM2-500M-Video-Instruct-f16.gguf
alias = ggml-org/SmolVLM2-500M-Video-Instruct-GGUF:Q8_0
; ctx-size range = 512..8192; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..32; chosen = 32
n-gpu-layers = 32
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = f16
cache-type-v = f16
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[lmstudio-community/Qwen3-8B-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3-8B-GGUF\Qwen3-8B-Q4_K_M.gguf
alias = lmstudio-community/Qwen3-8B-GGUF:Q4_K_M
; ctx-size range = 512..32768; chosen = 32768
ctx-size = 32768
; n-gpu-layers range = 0..36; chosen = 36
n-gpu-layers = 36
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = f16
cache-type-v = f16
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[lmstudio-community/Qwen3.5-35B-A3B-GGUF:Q6_K]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3.5-35B-A3B-GGUF\Qwen3.5-35B-A3B-Q6_K.gguf
mmproj = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3.5-35B-A3B-GGUF\mmproj-Qwen3.5-35B-A3B-BF16.gguf
alias = lmstudio-community/Qwen3.5-35B-A3B-GGUF:Q6_K
; ctx-size range = 512..262144; chosen = 43008
ctx-size = 43008
; n-gpu-layers range = 0..40; chosen = 40
n-gpu-layers = 40
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.7
top-k = 40
top-p = 0.95
min-p = 0.0
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true
; n-cpu-moe range = 0..40; chosen = 0
n-cpu-moe = 0

[lmstudio-community/Qwen3.5-4B-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3.5-4B-GGUF\Qwen3.5-4B-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3.5-4B-GGUF\mmproj-Qwen3.5-4B-BF16.gguf
alias = lmstudio-community/Qwen3.5-4B-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..32; chosen = 32
n-gpu-layers = 32
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[lmstudio-community/Qwen3.5-9B-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3.5-9B-GGUF\Qwen3.5-9B-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3.5-9B-GGUF\mmproj-Qwen3.5-9B-BF16.gguf
alias = lmstudio-community/Qwen3.5-9B-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..32; chosen = 32
n-gpu-layers = 32
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[lmstudio-community/Qwen3.6-35B-A3B-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3.6-35B-A3B-GGUF\Qwen3.6-35B-A3B-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\lmstudio-community\Qwen3.6-35B-A3B-GGUF\mmproj-Qwen3.6-35B-A3B-BF16.gguf
alias = lmstudio-community/Qwen3.6-35B-A3B-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 43008
ctx-size = 43008
; n-gpu-layers range = 0..40; chosen = 40
n-gpu-layers = 40
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.7
top-k = 40
top-p = 0.95
min-p = 0.0
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true
; n-cpu-moe range = 0..40; chosen = 0
n-cpu-moe = 0

[lmstudio-community/gemma-3-12b-it-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-3-12b-it-GGUF\gemma-3-12b-it-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-3-12b-it-GGUF\mmproj-model-f16.gguf
alias = lmstudio-community/gemma-3-12b-it-GGUF:Q4_K_M
; ctx-size range = 512..131072; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..48; chosen = 48
n-gpu-layers = 48
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[lmstudio-community/gemma-3-4b-it-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-3-4b-it-GGUF\gemma-3-4b-it-Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-3-4b-it-GGUF\mmproj-model-f16.gguf
alias = lmstudio-community/gemma-3-4b-it-GGUF:Q4_K_M
; ctx-size range = 512..131072; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..34; chosen = 34
n-gpu-layers = 34
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[lmstudio-community/gemma-3n-E4B-it-text-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-3n-E4B-it-text-GGUF\gemma-3n-E4B-it-Q4_K_M.gguf
alias = lmstudio-community/gemma-3n-E4B-it-text-GGUF:Q4_K_M
; ctx-size range = 512..32768; chosen = 32768
ctx-size = 32768
; n-gpu-layers range = 0..35; chosen = 35
n-gpu-layers = 35
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = f16
cache-type-v = f16
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[lmstudio-community/gemma-4-12B-it-QAT-GGUF:Q4_0]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-4-12B-it-QAT-GGUF\gemma-4-12B-it-QAT-Q4_0.gguf
mmproj = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-4-12B-it-QAT-GGUF\mmproj-gemma-4-12B-it-QAT-BF16.gguf
alias = lmstudio-community/gemma-4-12B-it-QAT-GGUF:Q4_0
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..48; chosen = 48
n-gpu-layers = 48
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true

[lmstudio-community/gemma-4-26B-A4B-it-GGUF:Q6_K]
model = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-4-26B-A4B-it-GGUF\gemma-4-26B-A4B-it-Q6_K.gguf
mmproj = E:\LMStudio\.lmstudio\models\lmstudio-community\gemma-4-26B-A4B-it-GGUF\mmproj-gemma-4-26B-A4B-it-BF16.gguf
alias = lmstudio-community/gemma-4-26B-A4B-it-GGUF:Q6_K
; ctx-size range = 512..262144; chosen = 43008
ctx-size = 43008
; n-gpu-layers range = 0..30; chosen = 30
n-gpu-layers = 30
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..2048; chosen = 2048
batch-size = 2048
; ubatch-size range = 32..2048; chosen = 512
ubatch-size = 512
; parallel range = 1..4; chosen = 4
parallel = 4
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.7
top-k = 40
top-p = 0.95
min-p = 0.0
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true
; n-cpu-moe range = 0..30; chosen = 0
n-cpu-moe = 0

[mradermacher/Qwen3-VL-8B-Abliterated-Caption-GGUF:Q4_K_M]
model = E:\LMStudio\.lmstudio\models\mradermacher\Qwen3-VL-8B-Abliterated-Caption-GGUF\Qwen3-VL-8B-Abliterated-Caption-it.Q4_K_M.gguf
mmproj = E:\LMStudio\.lmstudio\models\mradermacher\Qwen3-VL-8B-Abliterated-Caption-GGUF\Qwen3-VL-8B-Abliterated-Caption-it.mmproj-Q8_0.gguf
alias = mradermacher/Qwen3-VL-8B-Abliterated-Caption-GGUF:Q4_K_M
; ctx-size range = 512..262144; chosen = 8192
ctx-size = 8192
; n-gpu-layers range = 0..36; chosen = 36
n-gpu-layers = 36
; threads range = 1..20; chosen = 14
threads = 14
; batch-size range = 32..1024; chosen = 1024
batch-size = 1024
; ubatch-size range = 32..1024; chosen = 512
ubatch-size = 512
; parallel range = 1..1; chosen = 1
parallel = 1
; Heuristic sampling defaults / 经验采样默认值, not GGUF metadata-derived
temp = 0.8
top-k = 40
top-p = 0.95
min-p = 0.05
repeat-penalty = 1.0
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = true
kv-offload = true
mlock = true
mmap = true
seed = -1
flash-attn = true