AI Compatibility Tier List
Quadro RTX 6000 24GB
374 AI models ranked by how well they run on your 24 GB VRAM hardware. Best match: Qwen3-Coder 30B A3B Instruct (score: 96).
374
Models tested
295
Can run
24 GB
VRAM
70
Best tok/s
Tier Distribution
S 23
A 57
B 39
C 176
F 79
S: 23A: 57B: 39C: 176F: 79
S
S Tier -- Perfect Fit (23 models)
These models run flawlessly with headroom to spare.
Qwen3-Coder 30B A3B Instruct30.5B23.4 GB70 tok/s23K ctx
moe
Qwen3-VL 30B A3B Instruct30B23.1 GB73 tok/s26K ctx
moe
GPT-OSS 20B21B18.6 GB89 tok/s52K ctx
moe
Qwen 3 14B14B14.3 GB59 tok/s80K ctx
dense
Phi-4-reasoning-plus 14B14.7B15.3 GB56 tok/s33K ctx
dense
Qwen 3 30B A3B30.5B23.4 GB70 tok/s23K ctx
moe
Qwen 3.5 9B9B11.0 GB91 tok/s111K ctx
dense
Qwen 3.5 27B27B22.9 GB30 tok/s21K ctx
dense
Magistral Small 250724B20.4 GB34 tok/s40K ctx
dense
Devstral Small 2 24B Instruct24B20.4 GB34 tok/s40K ctx
dense
Qwen 3.6 27B27B20.7 GB23 tok/s69K ctx
dense
Qwen 3 8B8B10.4 GB102 tok/s115K ctx
dense
Devstral Small 1.124B20.4 GB34 tok/s40K ctx
dense
Nemotron Cascade 2 30B A3B30B24.5 GB50 tok/s13K ctx
moe
Nemotron 3 Nano 30B30B24.0 GB20 tok/s16K ctx
dense
Gemma 4 26B A4B25.2B22.3 GB75 tok/s23K ctx
moe
Ministral 3 14B14B14.3 GB58 tok/s80K ctx
multimodal
Codestral 2 25.0822B19.2 GB33 tok/s48K ctx
dense
CogVLM2 19B19B17.3 GB43 tok/s8K ctx
dense
Qwen 3.5 4B4B7.9 GB56 tok/s131K ctx
dense
Nemotron Nano 8B8B10.1 GB102 tok/s130K ctx
dense
Phi-4 14B14B14.9 GB58 tok/s16K ctx
dense
DeepSeek Coder V2 16B16B16.4 GB113 tok/s53K ctx
moe
A
A Tier -- Great Fit (57 models)
Excellent performance with comfortable memory margins.
Mistral Small 3.2 24B24B20.4 GB34 tok/s40K ctx
vision
Qwen 2.5 14B14B14.8 GB59 tok/s66K ctx
dense
Granite Code 20B20B18.7 GB41 tok/s8K ctx
dense
LFM2 24B24B20.4 GB34 tok/s40K ctx
dense
Phi-4 Mini Reasoning 4B3.8B7.1 GB53 tok/s131K ctx
dense
Gemma 3 12B12B15.5 GB50 tok/s44K ctx
dense
InternVL2 8B8B10.1 GB102 tok/s8K ctx
dense
Qwen 3.5 35B A3B35B26.1 GB39 tok/s4K ctx
moe
Mistral Small 24B24B20.4 GB34 tok/s33K ctx
dense
Mistral Small 3.1 24B24B20.4 GB34 tok/s40K ctx
dense
Ministral 3 8B8B10.4 GB102 tok/s115K ctx
multimodal
MiniCPM-V 2.6 8B8B10.1 GB102 tok/s2K ctx
dense
Nemotron Nano 9B v29B11.2 GB91 tok/s100K ctx
dense
SQLCoder 7B7B9.5 GB98 tok/s8K ctx
dense
OLMo 2 13B13B13.7 GB63 tok/s33K ctx
dense
Qwen 3 32B32B26.7 GB15 tok/s5K ctx
dense
Qwen 2.5 VL 7B7B8.4 GB98 tok/s33K ctx
dense
CodeLlama 7B Instruct7B15.4 GB98 tok/s16K ctx
dense
Qwen 3 4B4B7.9 GB56 tok/s33K ctx
dense
StarCoder 7B7B14.9 GB98 tok/s8K ctx
dense
Magistral 7B7B9.5 GB98 tok/s8K ctx
dense
DeepSeek R1 Distill 14B14B14.8 GB59 tok/s33K ctx
dense
CodeGeeX 4 9B9B9.4 GB92 tok/s131K ctx
dense
CodeLlama 13B Instruct13B23.4 GB59 tok/s16K ctx
dense
Gemma 4 E4B8B9.5 GB77 tok/s128K ctx
dense
Jina Embeddings v30.57B6.4 GB8 tok/s8K ctx
dense
Qwen 3.6 35B A3B35B28.8 GB29 tok/s4K ctx
moe
InternLM 7B7B15.4 GB98 tok/s8K ctx
dense
InternLM Chat 7B7B15.4 GB98 tok/s8K ctx
dense
Pixtral 12B12B13.1 GB68 tok/s88K ctx
dense
Granite Code 8B8B10.1 GB102 tok/s8K ctx
dense
LLaVA 1.6 13B13B23.4 GB59 tok/s4K ctx
dense
Granite 4.1 8B8B10.6 GB102 tok/s104K ctx
dense
DevStral 7B7B9.5 GB98 tok/s8K ctx
dense
Qwen 2.5 7B7B8.4 GB98 tok/s131K ctx
dense
BGE M30.57B5.6 GB8 tok/s8K ctx
dense
Nous Hermes 1.09B21.0 GB85 tok/s16K ctx
dense
Codestral Mamba 7B7B8.1 GB98 tok/s262K ctx
state-space
LLaVA 1.5 7B7B15.4 GB98 tok/s4K ctx
dense
EXAONE 4.0 32B32B26.7 GB15 tok/s5K ctx
dense
WizardLM 13B13B23.4 GB59 tok/s8K ctx
dense
Vicuna 13B13B23.4 GB59 tok/s4K ctx
dense
Llama 3.1 8B8B10.1 GB102 tok/s128K ctx
dense
Solar 7B7B10.5 GB98 tok/s8K ctx
dense
MPT-7B-Instruct7B15.4 GB98 tok/s8K ctx
dense
Baichuan 7B7B15.4 GB98 tok/s8K ctx
dense
mxbai Embed Large0.34B5.5 GB5 tok/s1K ctx
dense
GLM-4 9B9B9.4 GB92 tok/s128K ctx
dense
Qwen 2.5 32B32B26.7 GB15 tok/s5K ctx
dense
Qwen 2.5 Coder 3B3B7.3 GB42 tok/s131K ctx
dense
Nous Dolphin 13B13B24.9 GB34 tok/s15K ctx
dense
WizardMath 7B7B9.5 GB98 tok/s4K ctx
dense
OLMo 2 7B7B9.5 GB98 tok/s4K ctx
dense
Granite 4.1 30B30B25.5 GB17 tok/s10K ctx
dense
Snowflake Arctic Embed L0.34B5.5 GB5 tok/s1K ctx
dense
OLMo 2 32B32B26.7 GB15 tok/s4K ctx
dense
Gemma 4 E2B5.1B6.9 GB71 tok/s128K ctx
dense
B
B Tier -- Good Fit (39 models)
Solid performance, may need quantization or reduced context.
Qwen 2.5 Coder 7B7B8.4 GB98 tok/s131K ctx
dense
BGE Large EN v1.50.34B5.5 GB5 tok/s1K ctx
dense
Gemma 3 4B4B7.8 GB56 tok/s128K ctx
dense
Cerebras-GPT 13B13B22.4 GB51 tok/s19K ctx
dense
Qwen 2.5 Coder 14B14B14.8 GB59 tok/s66K ctx
dense
Gemma 2 9B9B13.9 GB67 tok/s8K ctx
dense
DeepSeek R1 Distill 8B8B10.1 GB102 tok/s33K ctx
dense
Phi 3 Mini 3.8B3.8B11.5 GB53 tok/s50K ctx
dense
Phi 4 Mini 4B4B7.2 GB56 tok/s128K ctx
dense
Ministral 3 3B3B5.9 GB42 tok/s262K ctx
multimodal
Baichuan 13B13B24.9 GB34 tok/s8K ctx
dense
Nomic Embed Text v1.50.14B4.1 GB2 tok/s8K ctx
dense
Samantha 7B7B9.5 GB98 tok/s4K ctx
dense
DeepSeek R1 Distill 7B7B8.4 GB98 tok/s33K ctx
dense
Phi 3.5 Mini 4B4B11.6 GB56 tok/s50K ctx
dense
Llama 3.2 11B Vision11B12.0 GB74 tok/s16K ctx
vision
Qwen 3.5 2B2B6.2 GB28 tok/s131K ctx
dense
Qwen 2.5 Coder 32B32B26.7 GB15 tok/s5K ctx
dense
Mistral Nemo 12B12B13.1 GB68 tok/s88K ctx
dense
Falcon 7B Instruct7B7.7 GB98 tok/s8K ctx
dense
Phi 3 Medium 14B14B14.9 GB58 tok/s64K ctx
dense
Qwen 2.5 3B3B7.3 GB42 tok/s131K ctx
dense
Granite Code 34B34B27.7 GB13 tok/s4K ctx
dense
Command R 35B35B27.1 GB13 tok/s4K ctx
dense
Codestral 22B22B19.2 GB35 tok/s33K ctx
dense
DeepSeek R1 Distill 32B32B26.7 GB15 tok/s5K ctx
dense
Yi Coder 9B9B10.3 GB92 tok/s131K ctx
dense
Qwen 3 1.7B1.7B6.0 GB24 tok/s33K ctx
dense
Mistral 7B Instruct v0.37B9.5 GB98 tok/s8K ctx
dense
Granite Code 3B3B7.6 GB42 tok/s8K ctx
dense
Granite 4.1 3B3B6.4 GB42 tok/s131K ctx
dense
All MiniLM L6 v20.02B3.6 GB2 tok/s0K ctx
dense
Ministral 8B8B10.4 GB102 tok/s115K ctx
dense
Qwen 2.5 Coder 1.5B1.5B4.6 GB21 tok/s33K ctx
dense
StarCoder 15B15B28.7 GB22 tok/s8K ctx
dense
Llama 3.2 3B3B6.8 GB42 tok/s128K ctx
dense
Vicuna 7B7B15.4 GB98 tok/s4K ctx
dense
Granite 3.1 8B8B10.1 GB112 tok/s128K ctx
state-space
Yi 1.5 9B9B10.3 GB92 tok/s4K ctx
dense
C
C Tier -- Tight Fit (176 models)
Runs with offloading or significant compromises.
StarCoder2 15B15B15.3 GB48 tok/s16K ctx
dense
Aya Expanse 32B32B25.3 GB17 tok/s8K ctx
dense
Codestral 22B v0.1
C5422B19.3 GB35 tok/s45K ctx
dense
Codestral RAG 19B Pruned i1
C5419B17.1 GB40 tok/s65K ctx
dense
Codestral 22B v0.1
C5422B19.3 GB35 tok/s45K ctx
dense
internlm2 5 20b chat
C5420B17.8 GB38 tok/s58K ctx
dense
internlm2 limarp chat 20b
C5420B17.8 GB38 tok/s58K ctx
dense
Qwen 2.5 Math 7B7B8.4 GB98 tok/s4K ctx
dense
internlm2 math plus 20b i1
C5420B17.8 GB38 tok/s58K ctx
dense
DeepSeek LLM 7B7B14.9 GB98 tok/s4K ctx
dense
Codestral 22B v0.1
C5322B19.3 GB35 tok/s45K ctx
dense
SmolLM3 3B3B7.1 GB42 tok/s128K ctx
dense
Codestral 21B Pruned i1
C5321B18.6 GB36 tok/s51K ctx
dense
Codestral 22B v0.1 IMat
C5322B19.3 GB35 tok/s45K ctx
dense
Codestral 22B v0.1 i1
C5322B19.3 GB35 tok/s45K ctx
dense
Phi 4 reasoning vision 15B
C5315B14.2 GB51 tok/s105K ctx
dense
StarCoder2 15B
C5315B14.2 GB51 tok/s105K ctx
dense
Aya Expanse 8B8B10.1 GB102 tok/s8K ctx
dense
DeepSeek R1 Distill Qwen 14B14B13.5 GB54 tok/s119K ctx
dense
OpenChat 7B7B9.5 GB98 tok/s8K ctx
dense
starcoder2 15b instruct v0.1
C5215B14.2 GB51 tok/s105K ctx
dense
starcoder2 15b i1
C5215B14.2 GB51 tok/s105K ctx
dense
starcoder2 15b instruct v0.1
C5215B14.2 GB51 tok/s105K ctx
dense
HelpingAI 15B i1
C5215B14.2 GB51 tok/s105K ctx
dense
NousResearch Hermes 4 14B
C5214B13.5 GB54 tok/s119K ctx
dense
DeepSeek R1 1.5B1.5B4.6 GB21 tok/s33K ctx
dense
GGUF SOLARized GraniStral 14B 2102 YeAM HCT 32QKV
C5214B13.5 GB54 tok/s119K ctx
dense
internlm JanusCoder 14B
C5214B13.5 GB54 tok/s119K ctx
dense
GGUF SOLARized GraniStral 14B 1902 YeAM HCT
C5214B13.5 GB54 tok/s119K ctx
dense
TinyLlama 1.1B1.1B4.3 GB15 tok/s4K ctx
dense
Dolphin 2.9 8B8B10.1 GB102 tok/s33K ctx
dense
gemma 3 12b it
C5212B12.0 GB63 tok/s152K ctx
dense
OpenHermes 2.5 7B7B9.5 GB98 tok/s8K ctx
dense
Zephyr 7B Beta7B9.5 GB98 tok/s33K ctx
dense
SOLAR 10.7B Instruct v1.0 uncensored
C5110.7B11.1 GB71 tok/s181K ctx
dense
Nous Hermes 2 SOLAR 10.7B
C5110.7B11.1 GB71 tok/s181K ctx
dense
Qwen3.5 9B9B9.8 GB85 tok/s231K ctx
dense
Qwen3.5 9B Uncensored HauhauCS Aggressive
C519B9.8 GB85 tok/s231K ctx
dense
Starling LM 7B7B9.5 GB98 tok/s8K ctx
dense
solar finalised finetuned Model 10.7B i1
C5110.7B11.1 GB71 tok/s181K ctx
dense
Qwen3.5 9B
C519B9.8 GB85 tok/s231K ctx
dense
StableLM 2 12B12B24.1 GB36 tok/s4K ctx
dense
Mistral Small 3.2 24B Instruct 250624B20.8 GB32 tok/s34K ctx
dense
SOLAR 10.7B v1.0
C5110.7B11.1 GB71 tok/s181K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C5124B20.8 GB32 tok/s34K ctx
dense
Mistral Small 24B Instruct 2501
C5124B20.8 GB32 tok/s34K ctx
dense
Qwen3.5 27B27B22.9 GB28 tok/s21K ctx
dense
Yi Coder 9B Chat
C509B9.8 GB85 tok/s231K ctx
dense
mistral small 3.1 24b instruct 2503 hf
C5024B20.8 GB32 tok/s34K ctx
dense
glm 4 9b chat 1m
C509B9.8 GB85 tok/s231K ctx
dense
cognitivecomputations Dolphin3.0 R1 Mistral 24B
C5024B20.8 GB32 tok/s34K ctx
dense
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored i1
C5024B20.8 GB32 tok/s34K ctx
dense
Meta Llama 3.1 8B Instruct
C508B9.1 GB95 tok/s270K ctx
dense
gemma 3 27b it27B22.9 GB28 tok/s21K ctx
dense
llava llama 3 8b v1 1
C508B9.1 GB95 tok/s270K ctx
dense
Yi 1.5 9B Chat
C509B9.8 GB85 tok/s231K ctx
dense
DeepSeek R1 0528 Qwen3 8B8B9.1 GB95 tok/s270K ctx
dense
HelpingAI2.5 10B i1
C5010B10.6 GB76 tok/s199K ctx
dense
Yi 1.5 34B34B27.7 GB13 tok/s4K ctx
dense
Helply 10.2b chat i1
C5010.2B10.7 GB75 tok/s194K ctx
dense
Meta Llama 3 8B Instruct
C508B9.1 GB95 tok/s270K ctx
dense
DeepSeek R1 Distill Llama 8B8B9.1 GB95 tok/s270K ctx
dense
Dolphin3.0 Llama3.1 8B
C508B9.1 GB95 tok/s270K ctx
dense
Llama 3 8B Instruct 32k v0.1
C508B9.1 GB95 tok/s270K ctx
dense
Meta Llama 3.1 8B Instruct
C508B9.1 GB95 tok/s270K ctx
dense
vntl llama3 8b v2
C508B9.1 GB95 tok/s270K ctx
dense
gemma 3 27b it
C5027B22.9 GB28 tok/s21K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C508B9.1 GB95 tok/s270K ctx
dense
cognitivecomputations Dolphin Mistral 24B Venice Edition
C5024B20.8 GB32 tok/s34K ctx
dense
DeepSeek R1 0528 Qwen3 8B
C508B9.1 GB95 tok/s270K ctx
dense
Yi 9B Coder i1
C509B9.8 GB85 tok/s231K ctx
dense
Qwen3 8B DeepSeek v3.2 Speciale Distill
C508B9.1 GB95 tok/s270K ctx
dense
Hermes 3 Llama 3.1 8B
C508B9.1 GB95 tok/s270K ctx
dense
HelpingAI2 9B
C509B9.8 GB85 tok/s231K ctx
dense
Hermes 2 Pro Llama 3 8B
C508B9.1 GB95 tok/s270K ctx
dense
Dolphin3.0 Llama3.1 8B
C508B9.1 GB95 tok/s270K ctx
dense
granite 8b code instruct 4k
C508B9.1 GB95 tok/s270K ctx
dense
HelpingAI2 9B i1
C509B9.8 GB85 tok/s231K ctx
dense
dolphin 2.9.4 llama3.1 8b
C508B9.1 GB95 tok/s270K ctx
dense
HelpingAI 9B 200k i1
C509B9.8 GB85 tok/s231K ctx
dense
HelpingAI 9B i1
C509B9.8 GB85 tok/s231K ctx
dense
openchat 3.6 8b 20240522 IMat
C508B9.1 GB95 tok/s270K ctx
dense
aya expanse 8b
C508B9.1 GB95 tok/s270K ctx
dense
dolphin v2 8b abliterated i1
C508B9.1 GB95 tok/s270K ctx
dense
EXAONE 3.5 7.8B Instruct
C507.8B9.0 GB98 tok/s279K ctx
dense
aya expanse 8b orthogonal heretic i1
C508B9.1 GB95 tok/s270K ctx
dense
Llama 2 7B Chat
C507B8.4 GB98 tok/s320K ctx
dense
EXAONE 3.5 7.8B Instruct
C507.8B9.0 GB98 tok/s279K ctx
dense
EXAONE 3.5 7.8B Instruct i1
C507.8B9.0 GB98 tok/s279K ctx
dense
Mistral 7B Instruct v0.2
C507B8.4 GB98 tok/s320K ctx
dense
exaone 3.0 7.8b it
C507.8B9.0 GB98 tok/s279K ctx
dense
Neural Chat 7B7B9.5 GB98 tok/s8K ctx
dense
aya expanse 8b orthogonal heretic
C508B9.1 GB95 tok/s270K ctx
dense
Mistral 7B Instruct v0.3
C507B8.4 GB98 tok/s320K ctx
dense
internlm2 5 1 8b chat i1
C508B9.1 GB95 tok/s270K ctx
dense
internlm3 8b instruct abliterated i1
C498B9.1 GB95 tok/s270K ctx
dense
Qwen 2.5 1.5B1.5B4.6 GB21 tok/s131K ctx
dense
Mistral 7B Instruct v0.3
C497B8.4 GB98 tok/s320K ctx
dense
Hermes 2 Pro Mistral 7B
C497B8.4 GB98 tok/s320K ctx
dense
zephyr 7B beta
C497B8.4 GB98 tok/s320K ctx
dense
Nous Hermes 2 Mistral 7B DPO
C497B8.4 GB98 tok/s320K ctx
dense
Falcon H1R 7B
C497B8.4 GB98 tok/s320K ctx
dense
falcon mamba 7b instruct Q4 K M
C497B8.4 GB98 tok/s320K ctx
dense
zephyr 7B alpha
C497B8.4 GB98 tok/s320K ctx
dense
speechless zephyr code functionary 7b
C497B8.4 GB98 tok/s320K ctx
dense
StarCoder2 7B
C497B8.4 GB98 tok/s320K ctx
dense
japanese stablelm instruct gamma 7B
C497B8.4 GB98 tok/s320K ctx
dense
Falcon H1 7B Instruct
C497B8.4 GB98 tok/s320K ctx
dense
Falcon H1R 7B7B8.4 GB98 tok/s320K ctx
dense
Mamba Codestral 7B v0.1
C497B8.4 GB98 tok/s320K ctx
dense
stabilityai japanese stablelm base gamma 7b
C497B8.4 GB98 tok/s320K ctx
dense
baichuan2 7b chat
C497B8.4 GB98 tok/s320K ctx
dense
DiscoPOP zephyr 7b gemma
C497B8.4 GB98 tok/s320K ctx
dense
starcoder2 7b
C497B8.4 GB98 tok/s320K ctx
dense
zephyr 7b beta Mistral 7B Instruct v0.2
C497B8.4 GB98 tok/s320K ctx
dense
OpenChat 3.5 7B Qwen v2.0 i1
C497B8.4 GB98 tok/s320K ctx
dense
OpenChat 3.5 7B Starling v2.0 i1
C497B8.4 GB98 tok/s320K ctx
dense
internlm2 math plus 7b IMat
C497B8.4 GB98 tok/s320K ctx
dense
CodeNinja 1.0 OpenChat 7B i1
C497B8.4 GB98 tok/s320K ctx
dense
internlm2 5 7b chat i1
C497B8.4 GB98 tok/s320K ctx
dense
OpenSafetyLab MD Judge v0 2 internlm2 7b
C497B8.4 GB98 tok/s320K ctx
dense
MD Judge v0 2 internlm2 7b i1
C497B8.4 GB98 tok/s320K ctx
dense
zephyr 7b gemma sft african ultrachat 100k
C497B8.4 GB98 tok/s320K ctx
dense
jointpreferences mistral 7b sft helpful
C497B8.4 GB98 tok/s320K ctx
dense
zephyr 7b dpo full i1
C497B8.4 GB98 tok/s320K ctx
dense
blossom v3 baichuan2 7b i1
C497B8.4 GB98 tok/s320K ctx
dense
blossom v1 baichuan 7b i1
C497B8.4 GB98 tok/s320K ctx
dense
Yi 1.5 6B Chat
C496B7.7 GB84 tok/s388K ctx
dense
stablelm 2 zephyr 1 6b
C486B7.7 GB84 tok/s388K ctx
dense
Yi 1.5 6B6B7.9 GB84 tok/s4K ctx
dense
StarCoder2 7B7B8.1 GB98 tok/s16K ctx
dense
Yi 1.5 6B Chat
C486B7.7 GB84 tok/s388K ctx
dense
stablelm 2 1 6b chat imatrix
C486B7.7 GB84 tok/s388K ctx
dense
Gemma 2 2B2B6.1 GB28 tok/s8K ctx
dense
HelpingAI2 6B
C486B7.7 GB84 tok/s388K ctx
dense
HelpingAI2 6B i1
C486B7.7 GB84 tok/s388K ctx
dense
Nemotron Mini 4B4B7.7 GB56 tok/s4K ctx
dense
Gemma 3 1B1B4.3 GB14 tok/s33K ctx
dense
HelpingAI2.5 5B i1
C475B6.9 GB70 tok/s482K ctx
dense
Qwen3.5 4B4B6.2 GB56 tok/s623K ctx
dense
Qwen 2.5 Coder 0.5B0.5B3.8 GB7 tok/s131K ctx
dense
gemma 3 4b it
C464B6.2 GB56 tok/s623K ctx
dense
gemma 3 4b it
C464B6.2 GB56 tok/s623K ctx
dense
Llama 3.2 3B Instruct
C453B5.8 GB42 tok/s844K ctx
dense
Qwen 3 0.6B0.6B4.5 GB8 tok/s33K ctx
dense
Qwen2.5 3B Instruct3B5.5 GB42 tok/s859K ctx
dense
Llama 3.2 1B1B4.4 GB14 tok/s128K ctx
dense
Llama 3.2 3B Instruct
C443B5.5 GB42 tok/s859K ctx
dense
Ministral 3 3B Instruct 2512
C443B5.5 GB42 tok/s859K ctx
dense
HELVETE 3B
C443B5.5 GB42 tok/s859K ctx
dense
Hermes 3 Llama 3.2 3B
C443B5.5 GB42 tok/s859K ctx
dense
stablelm zephyr 3b
C443B5.5 GB42 tok/s859K ctx
dense
StarCoder2 3B
C443B5.5 GB42 tok/s859K ctx
dense
AI21 Jamba Reasoning 3B
C443B5.5 GB42 tok/s859K ctx
dense
stablelm 3b 4e1t
C443B5.5 GB42 tok/s859K ctx
dense
ai21labs AI21 Jamba Reasoning 3B
C443B5.5 GB42 tok/s859K ctx
dense
ai21labs AI21 Jamba2 3B
C443B5.5 GB42 tok/s859K ctx
dense
HelpingAI 3B hindi i1
C443B5.5 GB42 tok/s859K ctx
dense
AI21 Jamba2 3B
C443B5.5 GB42 tok/s859K ctx
dense
HelpingAI 3B hindi
C443B5.5 GB42 tok/s859K ctx
dense
AI21 Jamba2 3B i1
C443B5.5 GB42 tok/s859K ctx
dense
gemma 2 2b it
C432B5.2 GB28 tok/s1301K ctx
dense
EXAONE 3.5 2.4B Instruct
C432.4B5.0 GB34 tok/s1094K ctx
dense
StarCoder2 3B3B5.6 GB42 tok/s16K ctx
dense
gemma 2b2B4.8 GB28 tok/s1330K ctx
dense
Gemmasutra Mini 2B v1
C432B4.8 GB28 tok/s1330K ctx
dense
gemma 2 2b it
C422B4.8 GB28 tok/s1330K ctx
dense
Qwen 3.5 0.6B0.6B4.5 GB8 tok/s131K ctx
dense
Qwen2.5 1.5B Instruct1.5B4.4 GB21 tok/s1801K ctx
dense
DeepSeek R1 Distill Qwen 1.5B1.5B4.4 GB21 tok/s1801K ctx
dense
Yi Coder 1.5B Chat
C411.5B4.4 GB21 tok/s1801K ctx
dense
stablelm 2 zephyr 1.6b
C411.6B4.5 GB22 tok/s1683K ctx
dense
logos16v2 stablelm2 1.6b i1
C411.6B4.5 GB22 tok/s1683K ctx
dense
Yi Coder 1.5B
C411.5B4.4 GB21 tok/s1801K ctx
dense
Falcon H1 1.5B Instruct1.5B4.4 GB21 tok/s1801K ctx
dense
TinyLlama 1.1B Chat v1.0
C401.1B4.1 GB15 tok/s2486K ctx
dense
F
F Tier -- Can't Run (79 models)
Too heavy for this hardware.
EXAONE 4.0 1.2B
D401.2B4.2 GB17 tok/s2272K ctx
dense
Llama 3.2 1B Instruct Q8 0
D401B4.2 GB14 tok/s2714K ctx
dense
TinyLlama 1.1B Chat v0.3
D401.1B4.1 GB15 tok/s2486K ctx
dense
Qwen 2.5 0.5B0.5B3.8 GB7 tok/s131K ctx
dense
TinyLlama 1.1B Chat v0.61.1B4.1 GB15 tok/s2486K ctx
dense
Llama 3.2 1B Instruct
D401B4.0 GB14 tok/s2743K ctx
dense
gemma 3 1b it
D401B4.0 GB14 tok/s2743K ctx
dense
TinyLlama 1.1B Chat v1.0 imatrix
D391.1B4.1 GB15 tok/s2486K ctx
dense
Falcon3 1B Instruct abliterated
D391B4.0 GB14 tok/s2743K ctx
dense
Yi 34B Chat34B27.7 GB13 tok/s4K ctx
dense
EXAONE 4.0 32B
D3832B26.6 GB14 tok/s5K ctx
dense
aya expanse 32b heretic MPOA i1
D3832B26.6 GB14 tok/s5K ctx
dense
Baichuan M2 32B Q4 K M
D3732B26.6 GB14 tok/s5K ctx
dense
SmolVLM 500M Instruct
D370.5B3.8 GB7 tok/s3246K ctx
dense
baichuan inc Baichuan M2 32B
D3732B26.6 GB14 tok/s5K ctx
dense
embeddinggemma 300M
D360.3B3.6 GB4 tok/s3273K ctx
dense
granite embedding 107m multilingual
D330.11B3.5 GB2 tok/s3302K ctx
dense
Falcon H1 Tiny 90M Instruct
D330.09B3.5 GB2 tok/s3303K ctx
dense
Qwen3.5 35B A3B35B28.8 GB11 tok/s4K ctx
dense
Qwen3.5 35B A3B
D3135B28.8 GB11 tok/s4K ctx
dense
Llama 3.1 70B70B50.9 GB2 tok/s4K ctx
dense
Llama 3.3 70B70B50.9 GB2 tok/s4K ctx
dense
Qwen 2.5 72B72B52.1 GB2 tok/s4K ctx
dense
Qwen 3 235B A22B235B149.5 GB2 tok/s4K ctx
moe
Qwen3-Coder-Next80B53.6 GB5 tok/s4K ctx
moe
Qwen3-Coder 480B A35B Instruct480B299.0 GB2 tok/s4K ctx
moe
Qwen 3.5 122B A10B122B80.2 GB3 tok/s4K ctx
moe
Qwen 3.5 397B A17B397B248.3 GB2 tok/s4K ctx
moe
Gemma 2 27B27B31.0 GB9 tok/s6K ctx
dense
Gemma 3 27B27B31.0 GB9 tok/s6K ctx
dense
Mixtral 8x7B47B33.9 GB11 tok/s4K ctx
moe
Mixtral 8x22B141B92.7 GB2 tok/s4K ctx
moe
Falcon 40B Instruct40B33.9 GB6 tok/s4K ctx
dense
MPT-30B-Instruct30B48.3 GB3 tok/s4K ctx
dense
Devstral 2 123B Instruct123B83.7 GB2 tok/s4K ctx
dense
Mistral Small 4 119B119B81.3 GB3 tok/s4K ctx
moe
Leanstral 119B A6B119B84.7 GB3 tok/s4K ctx
moe
Mistral Large 3675B420.4 GB2 tok/s4K ctx
moe
GLM-5744B476.2 GB2 tok/s4K ctx
moe
GLM-5.1754B482.3 GB2 tok/s4K ctx
moe
Kimi K2.51000B620.7 GB2 tok/s4K ctx
moe
Kimi K2.61000B620.7 GB2 tok/s4K ctx
moe
Kimi Linear 48B A3B48B33.5 GB6 tok/s4K ctx
linear
InternLM 20B20B36.0 GB10 tok/s6K ctx
dense
DeepSeek V3 671B671B472.2 GB2 tok/s4K ctx
moe
DeepSeek V3.1 671B671B472.2 GB2 tok/s4K ctx
moe
DeepSeek V4 Pro1600B867.2 GB2 tok/s4K ctx
moe
DeepSeek V4 Flash284B162.6 GB2 tok/s4K ctx
moe
DeepSeek R1 671B671B472.2 GB2 tok/s4K ctx
moe
DeepSeek Coder V2 236B236B205.9 GB2 tok/s4K ctx
moe
DeepSeek V2.5 236B236B205.9 GB2 tok/s4K ctx
moe
DeepSeek LLM 67B67B50.0 GB2 tok/s4K ctx
dense
Llama 4 Scout 17B 16E109B72.7 GB3 tok/s4K ctx
moe
Llama 4 Maverick 17B 128E400B250.2 GB2 tok/s4K ctx
moe
Command R+ 104B104B70.2 GB2 tok/s4K ctx
dense
Command A 111B111B74.9 GB2 tok/s4K ctx
dense
Pixtral Large 124B124B84.3 GB2 tok/s4K ctx
dense
Qwen 2.5 VL 72B72B52.1 GB2 tok/s4K ctx
dense
Qwen 2.5 Math 72B72B52.1 GB2 tok/s4K ctx
dense
Nemotron 70B70B50.9 GB2 tok/s4K ctx
dense
Llama 3.1 405B405B258.0 GB2 tok/s4K ctx
dense
DeepSeek R1 Distill 70B70B50.9 GB2 tok/s4K ctx
dense
GPT-OSS 120B117B79.6 GB2 tok/s4K ctx
dense
Gemma 4 31B30.7B36.7 GB6 tok/s4K ctx
dense
DeepSeek V3.2671B413.1 GB2 tok/s4K ctx
moe
MiniMax M2.7
F0230B147.4 GB2 tok/s4K ctx
moe
Solar Open 100B
F0100B76.0 GB2 tok/s4K ctx
dense
Qwen3 48B A4B Savant Commander Distill 12X Closed Open Heretic Uncensored
F048B38.2 GB4 tok/s4K ctx
dense
K EXAONE 236B A23B
F0236B174.9 GB2 tok/s4K ctx
dense
Llama 3.3 70B Instruct
F070B54.2 GB2 tok/s4K ctx
dense
Baichuan M3 235B
F0235B174.2 GB2 tok/s4K ctx
dense
Baichuan M3 235B i1
F0235B174.2 GB2 tok/s4K ctx
dense
BaichuanMed OCR 72B i1
F072B55.7 GB2 tok/s4K ctx
dense
Solar Open 100B i1
F0100B76.0 GB2 tok/s4K ctx
dense
Solar Open 69B REAP i1
F069B53.5 GB2 tok/s4K ctx
dense
Hermes 4.3 36B
F036B29.5 GB10 tok/s4K ctx
dense
stabilityai japanese stablelm instruct beta 70b
F070B54.2 GB2 tok/s4K ctx
dense
Qwen3.5 122B A10B122B77.4 GB2 tok/s4K ctx
dense
Qwen3.5 397B A17B397B292.0 GB2 tok/s4K ctx
dense
Compare with...
See How Other Hardware Stacks Up
Check tier lists for similar GPUs and Apple Silicon configs