Your rig
H200 SXM · 141 GB
32 GB system RAM · Hopper · 4800 GB/s · 139.4 GB usable VRAM
Which one should I actually run?
Best models for your H200 SXM
What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q4_K_M and 8K. 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. | Q4_K_M · 16.7 GB | 186 | Runs great |
| Best for coding | Ling 3.0 Flash 124B-A5B New inclusionAI · MIT |
SWE-bench Pro 56.6 claimed at 5B active — the 128 GB-class coding pick if you cannot fit DeepSeek V4. | Q4_K_M · 70.4 GB | 390 | Runs great |
| Best reasoning | Ling 3.0 Flash 124B-A5B New inclusionAI · MIT |
AIME 93 claimed at 5B active; hybrid attention keeps long reasoning traces cheap. | Q4_K_M · 70.4 GB | 390 | Runs great |
| Best for writing | Llama 3.3 70B Instruct Meta · Llama 3.3 Community |
The creative-writing favourite: consistent voice, takes direction, handles fiction framing. | Q4_K_M · 42.8 GB | 73 | 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. | Q4_K_M · 16.7 GB | 186 | Runs great |
| Best for agents | Ling 3.0 Flash 124B-A5B New inclusionAI · MIT |
Agentic workflows are what Ling 3.0 was trained for; MIT, 5B active. | Q4_K_M · 70.4 GB | 390 | 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. | Q4_K_M · 16.7 GB | 186 | 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. | Q4_K_M · 20.9 GB | 602 | 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. | Q4_K_M · 24.2 GB at 128K context |
186 | Runs great |
Everything that fits
Runs great
66 of 76 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 8K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q4_K_M | 70.3 GB | 0.19 GB | 71.1 GB |
68.3 GB free
|
199 | Ollama | Run |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q4_K_M | 69.7 GB | 0.06 GB | 70.4 GB |
69.0 GB free
|
166 | llama.cpp | Run |
| Ling 3.0 Flash 124B-A5B New | 124B MoE / 5.1B act | Q4_K_M | 69.7 GB | 0.06 GB | 70.4 GB |
69.0 GB free
|
390 | llama.cpp | Run |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q4_K_M | 66.9 GB | 0.18 GB | 67.7 GB |
71.7 GB free
|
306 | llama.cpp | Run |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 0.29 GB | 61.4 GB |
78.0 GB free
|
423 | Ollama | Run |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q4_K_M | 61.3 GB | 1.50 GB | 63.4 GB |
76.0 GB free
|
117 | Ollama | Run |
| Llama 3.3 70B Instruct | 70.6B | Q4_K_M | 39.7 GB | 2.50 GB | 42.8 GB |
96.6 GB free
|
73 | Ollama | Run |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q4_K_M | 39.7 GB | 2.50 GB | 42.8 GB |
96.6 GB free
|
73 | Ollama | Run |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q4_K_M | 20.2 GB | 0.16 GB | 20.9 GB |
118.5 GB free
|
602 | Ollama | Run |
| Ornith 1.5 35B-A3B New this week | 35.9B MoE / 3.3B act | Q4_K_M | 20.2 GB | 0.16 GB | 20.9 GB |
118.5 GB free
|
602 | Ollama | Run |
| LLM-jp 4 33B Thinking New this week | 33.2B | Q4_K_M | 18.7 GB | 2.00 GB | 21.3 GB |
118.1 GB free
|
156 | llama.cpp | Run |
| Qwen3 32B | 32.8B | Q4_K_M | 18.4 GB | 2.00 GB | 21.0 GB |
118.4 GB free
|
158 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q4_K_M | 18.4 GB | 2.00 GB | 21.0 GB |
118.4 GB free
|
158 | Ollama | Run |
| Qwen2.5-Coder 32B | 32.8B | Q4_K_M | 18.4 GB | 2.00 GB | 21.0 GB |
118.4 GB free
|
158 | Ollama | Run |
| Olmo 3.1 32B Instruct | 32.2B | Q4_K_M | 18.1 GB | 1.25 GB | 20.0 GB |
119.4 GB free
|
160 | Ollama | Run |
| Nemotron 3.5 Lightning 30B-A3B New | 31.6B MoE / 3.2B act | Q4_K_M | 17.8 GB | 0.05 GB | 18.4 GB |
121.0 GB free
|
621 | Ollama | Run |
| Gemma 4 31B | 31.3B | Q4_K_M | 17.6 GB | 2.03 GB | 20.2 GB |
119.2 GB free
|
165 | Ollama | Run |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q4_K_M | 17.5 GB | 0.41 GB | 18.6 GB |
120.8 GB free
|
663 | Ollama | Run |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q4_K_M | 17.1 GB | 0.75 GB | 18.5 GB |
120.9 GB free
|
602 | Ollama | Run |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q4_K_M | 17.1 GB | 0.75 GB | 18.5 GB |
120.9 GB free
|
602 | Ollama | Run |
| Muse Glimmer 30B New | 29.8B | Q4_K_M | 16.8 GB | 0.18 GB | 17.5 GB |
121.9 GB free
|
173 | Ollama | Run |
| Granite 4.1 30B | 28.9B | Q4_K_M | 16.3 GB | 2.00 GB | 18.9 GB |
120.5 GB free
|
179 | Ollama | Run |
| Qwen3.8 27B New this week | 27.8B | Q4_K_M | 15.6 GB | 0.50 GB | 16.7 GB |
122.7 GB free
|
186 | Ollama | Run |
| Qwen3.6 27B | 27.8B | Q4_K_M | 15.6 GB | 0.50 GB | 16.7 GB |
122.7 GB free
|
186 | Ollama | Run |
| Gemma 3 27B | 27.4B | Q4_K_M | 15.4 GB | 1.03 GB | 17.0 GB |
122.4 GB free
|
189 | Ollama | Run |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q4_K_M | 14.9 GB | 0.51 GB | 16.0 GB |
123.4 GB free
|
523 | Ollama | Run |
| Devstral Small 2 24B | 24B | Q4_K_M | 13.5 GB | 1.25 GB | 15.3 GB |
124.1 GB free
|
215 | llama.cpp | Run |
| Mistral Small 3.2 24B | 23.6B | Q4_K_M | 13.3 GB | 1.25 GB | 15.1 GB |
124.3 GB free
|
219 | Ollama | Run |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 0.19 GB | 11.6 GB |
127.8 GB free
|
599 | Ollama | Run |
| Qwen3 14B | 14.8B | Q4_K_M | 8.3 GB | 1.25 GB | 10.2 GB |
129.2 GB free
|
349 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q4_K_M | 8.3 GB | 1.50 GB | 10.4 GB |
129.0 GB free
|
349 | Ollama | Run |
| Qwen2.5-Coder 14B | 14.8B | Q4_K_M | 8.3 GB | 1.50 GB | 10.4 GB |
129.0 GB free
|
349 | Ollama | Run |
| Phi-4 14B | 14.7B | Q4_K_M | 8.3 GB | 1.56 GB | 10.4 GB |
129.0 GB free
|
352 | Ollama | Run |
| Ministral 3 14B | 13.9B | Q4_K_M | 7.8 GB | 1.25 GB | 9.7 GB |
129.7 GB free
|
372 | Ollama | Run |
| Gemma 3 12B | 12.2B | Q4_K_M | 6.9 GB | 0.81 GB | 8.3 GB |
131.1 GB free
|
424 | Ollama | Run |
| Mistral NeMo 12B | 12.2B | Q4_K_M | 6.9 GB | 1.25 GB | 8.7 GB |
130.7 GB free
|
424 | Ollama | Run |
| Gemma 4 12B | 12B | Q4_K_M | 6.7 GB | 0.81 GB | 8.2 GB |
131.2 GB free
|
431 | Ollama | Run |
| Qwen3.5 9B | 9.65B | Q4_K_M | 5.4 GB | 0.25 GB | 6.3 GB |
133.1 GB free
|
536 | Ollama | Run |
| Ornith 1.5 9B New this week | 9.41B | Q4_K_M | 5.3 GB | 0.25 GB | 6.1 GB |
133.3 GB free
|
549 | Ollama | Run |
| Ministral 3 8B | 8.92B | Q4_K_M | 5.0 GB | 1.06 GB | 6.7 GB |
132.7 GB free
|
579 | Ollama | Run |
| Granite 4.1 8B | 8.79B | Q4_K_M | 4.9 GB | 1.25 GB | 6.8 GB |
132.6 GB free
|
588 | Ollama | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q4_K_M | 4.8 GB | 0.09 GB | 5.5 GB |
133.9 GB free
|
1325 | Ollama | Run |
| Fara 7B | 8.29B | Q4_K_M | 4.7 GB | 0.44 GB | 5.7 GB |
133.7 GB free
|
623 | llama.cpp | Run |
| Qwen3 8B | 8.19B | Q4_K_M | 4.6 GB | 1.13 GB | 6.3 GB |
133.1 GB free
|
631 | Ollama | Run |
| Llama 3.1 8B Instruct | 8.03B | Q4_K_M | 4.5 GB | 1.00 GB | 6.1 GB |
133.3 GB free
|
644 | Ollama | Run |
| Gemma 4 E4B | 8.0B | Q4_K_M | 4.5 GB | 0.14 GB | 5.2 GB |
134.2 GB free
|
646 | Ollama | Run |
| Ling 3.0 Tiny 7.9B-A1.3B New | 7.9B MoE / 1.3B act | Q4_K_M | 4.4 GB | 0.05 GB | 5.1 GB |
134.3 GB free
|
1529 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q4_K_M | 4.3 GB | 0.44 GB | 5.3 GB |
134.1 GB free
|
678 | Ollama | Run |
| Qwen2.5-Coder 7B | 7.62B | Q4_K_M | 4.3 GB | 0.44 GB | 5.3 GB |
134.1 GB free
|
678 | Ollama | Run |
| Olmo 3 7B Instruct | 7.3B | Q4_K_M | 4.1 GB | 2.50 GB | 7.2 GB |
132.2 GB free
|
708 | Ollama | Run |
| Mistral 7B Instruct v0.3 | 7.25B | Q4_K_M | 4.1 GB | 1.00 GB | 5.7 GB |
133.7 GB free
|
713 | Ollama | Run |
| Gemma 4 E2B | 5.1B | Q4_K_M | 2.9 GB | 0.07 GB | 3.5 GB |
135.9 GB free
|
1013 | Ollama | Run |
| Qwen3.5 4B | 4.66B | Q4_K_M | 2.6 GB | 0.25 GB | 3.5 GB |
135.9 GB free
|
1109 | Ollama | Run |
| Gemma 3 4B | 4.3B | Q4_K_M | 2.4 GB | 0.30 GB | 3.3 GB |
136.1 GB free
|
1202 | Ollama | Run |
| Qwen3 4B | 4.02B | Q4_K_M | 2.3 GB | 1.13 GB | 4.0 GB |
135.4 GB free
|
1285 | Ollama | Run |
| Ministral 3 3B | 3.85B | Q4_K_M | 2.2 GB | 0.81 GB | 3.6 GB |
135.8 GB free
|
1342 | Ollama | Run |
| Phi-4-mini 3.8B | 3.84B | Q4_K_M | 2.2 GB | 1.00 GB | 3.8 GB |
135.6 GB free
|
1346 | Ollama | Run |
| Granite 4.1 3B | 3.4B | Q4_K_M | 1.9 GB | 0.63 GB | 3.1 GB |
136.3 GB free
|
1520 | Ollama | Run |
| Llama 3.2 3B Instruct | 3.21B | Q4_K_M | 1.8 GB | 0.88 GB | 3.3 GB |
136.1 GB free
|
1610 | Ollama | Run |
| LFM2.5 2.6B New | 2.7B | Q4_K_M | 1.5 GB | 0.13 GB | 2.2 GB |
137.2 GB free
|
1914 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q4_K_M | 1.3 GB | 0.09 GB | 2.0 GB |
137.4 GB free
|
2277 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q4_K_M | 1.0 GB | 0.88 GB | 2.4 GB |
137.0 GB free
|
3004 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q4_K_M | 0.7 GB | 0.25 GB | 1.5 GB |
137.9 GB free
|
4168 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q4_K_M | 0.6 GB | 0.04 GB | 1.2 GB |
138.2 GB free
|
5168 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q4_K_M | 0.5 GB | 0.09 GB | 1.2 GB |
138.2 GB free
|
5940 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q4_K_M | 0.3 GB | 0.88 GB | 1.8 GB |
137.6 GB free
|
8613 | Ollama | Run |
Runs — tight
1 model · fits at 8K, drop context or quant to go longer| Model | Params | Quant | Weights | +KV 8K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3 235B-A22B | 235B MoE / 22B act | Q4_K_M | 132.1 GB | 1.47 GB | 134.2 GB |
5.2 GB free
|
90 | llama.cpp | Run |
Won't fit in VRAM
9 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 8K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 284B-A13B New | 284B MoE / 13B act | Q4_K_M | 159.7 GB | 0.38 GB | 160.7 GB | +21.3 GB | ~13 | llama.cpp | Why |
| Kimi K3 2.8T-A104B New | 2780B MoE / 104B act | Q4_K_M | 1563.2 GB | 0.21 GB | 1564.0 GB | +1424.6 GB | ~0.3 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B New | 2446B MoE / 95B act | Q4_K_M | 1375.4 GB | 0.72 GB | 1376.7 GB | +1237.3 GB | ~0.3 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B New | 1650B MoE / 49B act | Q4_K_M | 927.8 GB | 0.54 GB | 928.9 GB | +789.5 GB | ~0.6 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q4_K_M | 577.5 GB | 0.54 GB | 578.6 GB | +439.2 GB | ~1.0 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q4_K_M | 423.4 GB | 0.69 GB | 424.7 GB | +285.3 GB | ~0.9 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q4_K_M | 377.3 GB | 0.54 GB | 378.4 GB | +239.0 GB | ~1.1 | llama.cpp | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q4_K_M | 226.6 GB | 0.23 GB | 227.4 GB | +88.0 GB | ~3.7 | llama.cpp | Why |
| Ornith 1.5 397B-A17B New this week | 397B MoE / 17B act | Q4_K_M | 223.2 GB | 0.23 GB | 224.1 GB | +84.7 GB | ~3.8 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 8K tokens + 0.6 GB runtime overhead, against 139.4 GB usable VRAM (141 GB less display and driver reserve). Tokens per second are estimated from 4800 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.