Your rig
RTX A6000 · 48 GB
8 GB system RAM · Ampere · 768 GB/s · 46.4 GB usable VRAM
Which one should I actually run?
Best models for your RTX A6000
What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q3_K_M and 32K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.
All
General assistantCodingReasoning & mathsWritingVisionAgents & tool useTranslationLow latencyLong context
| Recommendation | Model | Why | Quant · total | Tok/s est. | |
|---|---|---|---|---|---|
| Best overall | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
Best capability per gigabyte: a current-generation dense 27B with vision and 262K context. | Q3_K_M · 15.3 GB | 37 | Runs great |
| Best for coding | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
Terminal-Bench 73, DeepSWE 42 — a generation ahead of anything else that fits 24 GB. | Q3_K_M · 15.3 GB | 37 | Runs great |
| Best reasoning | Gemma 4 31B Google · Apache 2.0 |
89% AIME — the strongest maths of any model under 32B. | Q3_K_M · 20.6 GB | 33 | Runs great |
| Best for writing | Gemma 4 31B Google · Apache 2.0 |
The cleanest, least verbose prose of the 2026 24–32 GB class. | Q3_K_M · 20.6 GB | 33 | Runs great |
| Best vision | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
Image and video in, OSWorld 84 — the strongest local vision-language model at 24 GB. | Q3_K_M · 15.3 GB | 37 | Runs great |
| Best for agents | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
Computer use and tool calling are what 3.8 was trained for (OSWorld 84). | Q3_K_M · 15.3 GB | 37 | Runs great |
| Best translation | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
119 languages, and Qwen translations read as idiomatic rather than literal. | Q3_K_M · 15.3 GB | 37 | Runs great |
| Fastest good model | Qwen3.6 35B-A3B Alibaba · Apache 2.0 |
3.3B active per token: the fastest model that still competes with dense 27Bs. | Q3_K_M · 17.6 GB | 119 | Runs great |
| Best long context | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
262K native, and only 16 of 64 blocks keep a KV cache — long context is cheap here. | Q3_K_M · 21.3 GB at 128K context |
37 | Runs great |
Everything that fits
Runs great
58 of 76 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 32K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q3_K_M | 16.3 GB | 0.63 GB | 17.6 GB |
28.8 GB free
|
119 | Ollama | Run |
| Ornith 1.5 35B-A3B New this week | 35.9B MoE / 3.3B act | Q3_K_M | 16.3 GB | 0.63 GB | 17.6 GB |
28.8 GB free
|
119 | Ollama | Run |
| LLM-jp 4 33B Thinking New this week | 33.2B | Q3_K_M | 15.1 GB | 8.00 GB | 23.7 GB |
22.7 GB free
|
31 | llama.cpp | Run |
| Qwen3 32B | 32.8B | Q3_K_M | 14.9 GB | 8.00 GB | 23.5 GB |
22.9 GB free
|
31 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q3_K_M | 14.9 GB | 8.00 GB | 23.5 GB |
22.9 GB free
|
31 | Ollama | Run |
| Qwen2.5-Coder 32B | 32.8B | Q3_K_M | 14.9 GB | 8.00 GB | 23.5 GB |
22.9 GB free
|
31 | Ollama | Run |
| Olmo 3.1 32B Instruct | 32.2B | Q3_K_M | 14.7 GB | 2.75 GB | 18.0 GB |
28.4 GB free
|
32 | Ollama | Run |
| Nemotron 3.5 Lightning 30B-A3B New | 31.6B MoE / 3.2B act | Q3_K_M | 14.4 GB | 0.19 GB | 15.2 GB |
31.2 GB free
|
123 | Ollama | Run |
| Gemma 4 31B | 31.3B | Q3_K_M | 14.2 GB | 5.78 GB | 20.6 GB |
25.8 GB free
|
33 | Ollama | Run |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q3_K_M | 14.2 GB | 1.65 GB | 16.5 GB |
29.9 GB free
|
131 | Ollama | Run |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q3_K_M | 13.9 GB | 3.00 GB | 17.5 GB |
28.9 GB free
|
119 | Ollama | Run |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q3_K_M | 13.9 GB | 3.00 GB | 17.5 GB |
28.9 GB free
|
119 | Ollama | Run |
| Muse Glimmer 30B New | 29.8B | Q3_K_M | 13.6 GB | 0.48 GB | 14.6 GB |
31.8 GB free
|
34 | Ollama | Run |
| Granite 4.1 30B | 28.9B | Q3_K_M | 13.2 GB | 8.00 GB | 21.8 GB |
24.6 GB free
|
35 | Ollama | Run |
| Qwen3.8 27B New this week | 27.8B | Q3_K_M | 12.7 GB | 2.00 GB | 15.3 GB |
31.1 GB free
|
37 | Ollama | Run |
| Qwen3.6 27B | 27.8B | Q3_K_M | 12.7 GB | 2.00 GB | 15.3 GB |
31.1 GB free
|
37 | Ollama | Run |
| Gemma 3 27B | 27.4B | Q3_K_M | 12.5 GB | 2.91 GB | 16.0 GB |
30.4 GB free
|
37 | Ollama | Run |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q3_K_M | 12.1 GB | 1.45 GB | 14.1 GB |
32.3 GB free
|
103 | Ollama | Run |
| Devstral Small 2 24B | 24B | Q3_K_M | 10.9 GB | 5.00 GB | 16.5 GB |
29.9 GB free
|
43 | llama.cpp | Run |
| Mistral Small 3.2 24B | 23.6B | Q3_K_M | 10.7 GB | 5.00 GB | 16.3 GB |
30.1 GB free
|
43 | Ollama | Run |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 0.75 GB | 12.2 GB |
34.2 GB free
|
96 | Ollama | Run |
| Qwen3 14B | 14.8B | Q3_K_M | 6.7 GB | 5.00 GB | 12.3 GB |
34.1 GB free
|
69 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q3_K_M | 6.7 GB | 6.00 GB | 13.3 GB |
33.1 GB free
|
69 | Ollama | Run |
| Qwen2.5-Coder 14B | 14.8B | Q3_K_M | 6.7 GB | 6.00 GB | 13.3 GB |
33.1 GB free
|
69 | Ollama | Run |
| Phi-4 14B | 14.7B | Q3_K_M | 6.7 GB | 3.13 GB | 10.4 GB |
36.0 GB free
|
69 | Ollama | Run |
| Ministral 3 14B | 13.9B | Q3_K_M | 6.3 GB | 5.00 GB | 11.9 GB |
34.5 GB free
|
73 | Ollama | Run |
| Gemma 3 12B | 12.2B | Q3_K_M | 5.6 GB | 2.31 GB | 8.5 GB |
37.9 GB free
|
84 | Ollama | Run |
| Mistral NeMo 12B | 12.2B | Q3_K_M | 5.6 GB | 5.00 GB | 11.2 GB |
35.2 GB free
|
84 | Ollama | Run |
| Gemma 4 12B | 12B | Q3_K_M | 5.5 GB | 2.31 GB | 8.4 GB |
38.0 GB free
|
85 | Ollama | Run |
| Qwen3.5 9B | 9.65B | Q3_K_M | 4.4 GB | 1.00 GB | 6.0 GB |
40.4 GB free
|
106 | Ollama | Run |
| Ornith 1.5 9B New this week | 9.41B | Q3_K_M | 4.3 GB | 1.00 GB | 5.9 GB |
40.5 GB free
|
109 | Ollama | Run |
| Ministral 3 8B | 8.92B | Q3_K_M | 4.1 GB | 4.25 GB | 8.9 GB |
37.5 GB free
|
115 | Ollama | Run |
| Granite 4.1 8B | 8.79B | Q3_K_M | 4.0 GB | 5.00 GB | 9.6 GB |
36.8 GB free
|
116 | Ollama | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q3_K_M | 3.9 GB | 0.38 GB | 4.8 GB |
41.6 GB free
|
262 | Ollama | Run |
| Fara 7B | 8.29B | Q3_K_M | 3.8 GB | 1.75 GB | 6.1 GB |
40.3 GB free
|
123 | llama.cpp | Run |
| Qwen3 8B | 8.19B | Q3_K_M | 3.7 GB | 4.50 GB | 8.8 GB |
37.6 GB free
|
125 | Ollama | Run |
| Llama 3.1 8B Instruct | 8.03B | Q3_K_M | 3.7 GB | 4.00 GB | 8.3 GB |
38.1 GB free
|
127 | Ollama | Run |
| Gemma 4 E4B | 8.0B | Q3_K_M | 3.6 GB | 0.47 GB | 4.7 GB |
41.7 GB free
|
128 | Ollama | Run |
| Ling 3.0 Tiny 7.9B-A1.3B New | 7.9B MoE / 1.3B act | Q3_K_M | 3.6 GB | 0.21 GB | 4.4 GB |
42.0 GB free
|
302 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q3_K_M | 3.5 GB | 1.75 GB | 5.8 GB |
40.6 GB free
|
134 | Ollama | Run |
| Qwen2.5-Coder 7B | 7.62B | Q3_K_M | 3.5 GB | 1.75 GB | 5.8 GB |
40.6 GB free
|
134 | Ollama | Run |
| Olmo 3 7B Instruct | 7.3B | Q3_K_M | 3.3 GB | 5.50 GB | 9.4 GB |
37.0 GB free
|
140 | Ollama | Run |
| Mistral 7B Instruct v0.3 | 7.25B | Q3_K_M | 3.3 GB | 4.00 GB | 7.9 GB |
38.5 GB free
|
141 | Ollama | Run |
| Gemma 4 E2B | 5.1B | Q3_K_M | 2.3 GB | 0.23 GB | 3.2 GB |
43.2 GB free
|
200 | Ollama | Run |
| Qwen3.5 4B | 4.66B | Q3_K_M | 2.1 GB | 1.00 GB | 3.7 GB |
42.7 GB free
|
219 | Ollama | Run |
| Gemma 3 4B | 4.3B | Q3_K_M | 2.0 GB | 0.86 GB | 3.4 GB |
43.0 GB free
|
238 | Ollama | Run |
| Qwen3 4B | 4.02B | Q3_K_M | 1.8 GB | 4.50 GB | 6.9 GB |
39.5 GB free
|
254 | Ollama | Run |
| Ministral 3 3B | 3.85B | Q3_K_M | 1.8 GB | 3.25 GB | 5.6 GB |
40.8 GB free
|
265 | Ollama | Run |
| Phi-4-mini 3.8B | 3.84B | Q3_K_M | 1.7 GB | 4.00 GB | 6.3 GB |
40.1 GB free
|
266 | Ollama | Run |
| Granite 4.1 3B | 3.4B | Q3_K_M | 1.5 GB | 2.50 GB | 4.6 GB |
41.8 GB free
|
300 | Ollama | Run |
| Llama 3.2 3B Instruct | 3.21B | Q3_K_M | 1.5 GB | 3.50 GB | 5.6 GB |
40.8 GB free
|
318 | Ollama | Run |
| LFM2.5 2.6B New | 2.7B | Q3_K_M | 1.2 GB | 0.50 GB | 2.3 GB |
44.1 GB free
|
378 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q3_K_M | 1.0 GB | 0.38 GB | 2.0 GB |
44.4 GB free
|
450 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q3_K_M | 0.8 GB | 3.50 GB | 4.9 GB |
41.5 GB free
|
594 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q3_K_M | 0.6 GB | 1.00 GB | 2.2 GB |
44.2 GB free
|
824 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q3_K_M | 0.5 GB | 0.14 GB | 1.2 GB |
45.2 GB free
|
1021 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q3_K_M | 0.4 GB | 0.38 GB | 1.4 GB |
45.0 GB free
|
1174 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q3_K_M | 0.3 GB | 3.50 GB | 4.4 GB |
42.0 GB free
|
1702 | Ollama | Run |
Runs — tight
2 models · fits at 32K, drop context or quant to go longer| Model | Params | Quant | Weights | +KV 32K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Llama 3.3 70B Instruct | 70.6B | Q3_K_M | 32.1 GB | 10.00 GB | 42.7 GB |
3.7 GB free
|
14 | llama.cpp | Run |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q3_K_M | 32.1 GB | 10.00 GB | 42.7 GB |
3.7 GB free
|
14 | llama.cpp | Run |
Won't fit in VRAM
16 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 32K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q3_K_M | 49.6 GB | 2.63 GB | 52.8 GB | +6.4 GB | ~9.1 | llama.cpp | Why |
| Kimi K3 2.8T-A104B New | 2780B MoE / 104B act | Q3_K_M | 1265.4 GB | 0.84 GB | 1266.9 GB | +1220.5 GB | ~0.3 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B New | 2446B MoE / 95B act | Q3_K_M | 1113.4 GB | 2.88 GB | 1116.9 GB | +1070.5 GB | ~0.3 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B New | 1650B MoE / 49B act | Q3_K_M | 751.1 GB | 2.14 GB | 753.8 GB | +707.4 GB | ~0.7 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q3_K_M | 467.5 GB | 2.14 GB | 470.2 GB | +423.8 GB | ~1.0 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q3_K_M | 342.8 GB | 2.74 GB | 346.1 GB | +299.7 GB | ~0.9 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q3_K_M | 305.4 GB | 2.14 GB | 308.2 GB | +261.8 GB | ~1.0 | llama.cpp | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q3_K_M | 183.4 GB | 0.94 GB | 185.0 GB | +138.6 GB | ~2.3 | llama.cpp | Why |
| Ornith 1.5 397B-A17B New this week | 397B MoE / 17B act | Q3_K_M | 180.7 GB | 0.94 GB | 182.2 GB | +135.8 GB | ~2.3 | llama.cpp | Why |
| DeepSeek V4 Flash 284B-A13B New | 284B MoE / 13B act | Q3_K_M | 129.3 GB | 1.51 GB | 131.4 GB | +85.0 GB | ~3.5 | llama.cpp | Why |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q3_K_M | 107.0 GB | 5.88 GB | 113.4 GB | +67.0 GB | ~2.1 | llama.cpp | Why |
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q3_K_M | 56.9 GB | 0.75 GB | 58.2 GB | +11.8 GB | ~11 | llama.cpp | Why |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q3_K_M | 56.4 GB | 0.25 GB | 57.3 GB | +10.9 GB | ~10 | llama.cpp | Why |
| Ling 3.0 Flash 124B-A5B New | 124B MoE / 5.1B act | Q3_K_M | 56.4 GB | 0.25 GB | 57.3 GB | +10.9 GB | ~24 | llama.cpp | Why |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q3_K_M | 54.2 GB | 0.70 GB | 55.5 GB | +9.1 GB | ~20 | llama.cpp | Why |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 1.13 GB | 62.2 GB | +15.8 GB | ~17 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 32K tokens + 0.6 GB runtime overhead, against 46.4 GB usable VRAM (48 GB less display and driver reserve). Tokens per second are estimated from 768 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.