Your rig

H100 PCIe · 80 GB

128 GB system RAM · Hopper · 2000 GB/s · 78.4 GB usable VRAM
Edit hardware Export as JSON

Context length

KV cache at f16, 32K tokens

Quality floor
Q8_0 — near-lossless Q6_K Q5_K_M Q4_K_M — recommended Q3_K_M Q2_K — damaged
KV cache type
System RAM (GB)
Runtime
Ollamallama.cppLM StudiovLLM

4 of 5 runtimes drive this device.

Allow CPU offload Include partial-offload fits

Offloaded layers run at 60 GB/s host bandwidth — expect single-digit tokens per second.

Which one should I actually run?

Best models for your H100 PCIe

Updated 8 Oct 2026 1 new this month

What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q5_K_M and 32K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.

RecommendationModelWhyQuant · totalTok/s est.
Best overall Qwen3.8 27B
Alibaba · Apache 2.0
Best capability per gigabyte: a current-generation dense 27B with vision and 262K context. Q5_K_M · 21.0 GB 66 Runs great
Best for coding Qwen3.8 27B
Alibaba · Apache 2.0
Terminal-Bench 73, DeepSWE 42 — a generation ahead of anything else that fits 24 GB. Q5_K_M · 21.0 GB 66 Runs great
Best reasoning Gemma 4 31B
Google · Apache 2.0
89% AIME — the strongest maths of any model under 32B. Q5_K_M · 27.0 GB 59 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. Q5_K_M · 57.2 GB 26 Runs great
Best vision Qwen3.8 27B
Alibaba · Apache 2.0
Image and video in, OSWorld 84 — the strongest local vision-language model at 24 GB. Q5_K_M · 21.0 GB 66 Runs great
Best for agents Qwen3.8 27B
Alibaba · Apache 2.0
Computer use and tool calling are what 3.8 was trained for (OSWorld 84). Q5_K_M · 21.0 GB 66 Runs great
Best translation Qwen3.8 27B
Alibaba · Apache 2.0
119 languages, and Qwen translations read as idiomatic rather than literal. Q5_K_M · 21.0 GB 66 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. Q5_K_M · 24.9 GB 214 Runs great
Best long context Qwen3.8 27B
Alibaba · Apache 2.0
262K native, and only 16 of 64 blocks keep a KV cache — long context is cheap here. Q5_K_M · 27.0 GB
at 128K context
66 Runs great

Everything that fits

Runs great

61 of 80 · fits with headroom for a longer prompt
ModelParamsQuantWeights +KV 32KTotal VRAM headroom Tok/sRuntime
gpt-oss 120B 117B MoE / 5.1B act MXFP4 60.5 GB 1.13 GB 62.2 GB
16.2 GB free
176 Ollama Run
Llama 3.3 70B Instruct 70.6B Q5_K_M 46.6 GB 10.00 GB 57.2 GB
21.2 GB free
26 Ollama Run
DeepSeek-R1-Distill-Llama 70B 70.6B Q5_K_M 46.6 GB 10.00 GB 57.2 GB
21.2 GB free
26 Ollama Run
Qwen3.6 35B-A3B 35.9B MoE / 3.3B act Q5_K_M 23.7 GB 0.63 GB 24.9 GB
53.5 GB free
214 Ollama Run
Ornith 1.5 35B-A3B 35.9B MoE / 3.3B act Q5_K_M 23.7 GB 0.63 GB 24.9 GB
53.5 GB free
214 Ollama Run
LLM-jp 4 33B Thinking 33.2B Q5_K_M 21.9 GB 8.00 GB 30.5 GB
47.9 GB free
55 llama.cpp Run
Qwen3 32B 32.8B Q5_K_M 21.7 GB 8.00 GB 30.3 GB
48.1 GB free
56 Ollama Run
DeepSeek-R1-Distill-Qwen 32B 32.8B Q5_K_M 21.7 GB 8.00 GB 30.3 GB
48.1 GB free
56 Ollama Run
Qwen2.5-Coder 32B 32.8B Q5_K_M 21.7 GB 8.00 GB 30.3 GB
48.1 GB free
56 Ollama Run
Olmo 3.1 32B Instruct 32.2B Q5_K_M 21.3 GB 2.75 GB 24.6 GB
53.8 GB free
57 Ollama Run
Nemotron 3.5 Lightning 30B-A3B 31.6B MoE / 3.2B act Q5_K_M 20.9 GB 0.19 GB 21.6 GB
56.8 GB free
220 Ollama Run
Gemma 4 31B 31.3B Q5_K_M 20.7 GB 5.78 GB 27.0 GB
51.4 GB free
59 Ollama Run
GLM-4.7-Flash 30B-A3B 31.2B MoE / 3B act Q5_K_M 20.6 GB 1.65 GB 22.8 GB
55.6 GB free
235 Ollama Run
Qwen3 30B-A3B 30.5B MoE / 3.3B act Q5_K_M 20.1 GB 3.00 GB 23.7 GB
54.7 GB free
214 Ollama Run
Qwen3 Coder 30B-A3B 30.5B MoE / 3.3B act Q5_K_M 20.1 GB 3.00 GB 23.7 GB
54.7 GB free
214 Ollama Run
Muse Glimmer 30B 29.8B Q5_K_M 19.7 GB 0.48 GB 20.8 GB
57.6 GB free
62 Ollama Run
Granite 4.1 30B 28.9B Q5_K_M 19.1 GB 8.00 GB 27.7 GB
50.7 GB free
63 Ollama Run
Qwen3.8 27B 27.8B Q5_K_M 18.4 GB 2.00 GB 21.0 GB
57.4 GB free
66 Ollama Run
Qwen3.6 27B 27.8B Q5_K_M 18.4 GB 2.00 GB 21.0 GB
57.4 GB free
66 Ollama Run
Gemma 3 27B 27.4B Q5_K_M 18.1 GB 2.91 GB 21.6 GB
56.8 GB free
67 Ollama Run
Gemma 4 26B-A4B 26.5B MoE / 3.8B act Q5_K_M 17.5 GB 1.45 GB 19.5 GB
58.9 GB free
186 Ollama Run
Devstral Small 2 24B 24B Q5_K_M 15.8 GB 5.00 GB 21.4 GB
57.0 GB free
76 llama.cpp Run
Mistral Small 3.2 24B 23.6B Q5_K_M 15.6 GB 5.00 GB 21.2 GB
57.2 GB free
78 Ollama Run
gpt-oss 20B 20.9B MoE / 3.6B act MXFP4 10.8 GB 0.75 GB 12.2 GB
66.2 GB free
250 Ollama Run
Qwen3 14B 14.8B Q5_K_M 9.8 GB 5.00 GB 15.4 GB
63.0 GB free
124 Ollama Run
DeepSeek-R1-Distill-Qwen 14B 14.8B Q5_K_M 9.8 GB 6.00 GB 16.4 GB
62.0 GB free
124 Ollama Run
Qwen2.5-Coder 14B 14.8B Q5_K_M 9.8 GB 6.00 GB 16.4 GB
62.0 GB free
124 Ollama Run
Phi-4 14B 14.7B Q5_K_M 9.7 GB 3.13 GB 13.4 GB
65.0 GB free
125 Ollama Run
Ministral 3 14B 13.9B Q5_K_M 9.2 GB 5.00 GB 14.8 GB
63.6 GB free
132 Ollama Run
Gemma 3 12B 12.2B Q5_K_M 8.1 GB 2.31 GB 11.0 GB
67.4 GB free
150 Ollama Run
Mistral NeMo 12B 12.2B Q5_K_M 8.1 GB 5.00 GB 13.7 GB
64.7 GB free
150 Ollama Run
Gemma 4 12B 12B Q5_K_M 7.9 GB 2.31 GB 10.8 GB
67.6 GB free
153 Ollama Run
Qwen3.5 9B 9.65B Q5_K_M 6.4 GB 1.00 GB 8.0 GB
70.4 GB free
190 Ollama Run
Ornith 1.5 9B 9.41B Q5_K_M 6.2 GB 1.00 GB 7.8 GB
70.6 GB free
195 Ollama Run
Ministral 3 8B 8.92B Q5_K_M 5.9 GB 4.25 GB 10.7 GB
67.7 GB free
206 Ollama Run
Granite 4.1 8B 8.79B Q5_K_M 5.8 GB 5.00 GB 11.4 GB
67.0 GB free
209 Ollama Run
LFM2.5 8B-A1B 8.47B MoE / 1.5B act Q5_K_M 5.6 GB 0.38 GB 6.6 GB
71.8 GB free
470 Ollama Run
Fara 7B 8.29B Q5_K_M 5.5 GB 1.75 GB 7.8 GB
70.6 GB free
221 llama.cpp Run
Qwen3 8B 8.19B Q5_K_M 5.4 GB 4.50 GB 10.5 GB
67.9 GB free
224 Ollama Run
Llama 3.1 8B Instruct 8.03B Q5_K_M 5.3 GB 4.00 GB 9.9 GB
68.5 GB free
228 Ollama Run
Gemma 4 E4B 8.0B Q5_K_M 5.3 GB 0.47 GB 6.4 GB
72.0 GB free
229 Ollama Run
Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE / 1.3B act Q5_K_M 5.2 GB 0.21 GB 6.0 GB
72.4 GB free
543 llama.cpp Run
DeepSeek-R1-Distill-Qwen 7B 7.62B Q5_K_M 5.0 GB 1.75 GB 7.4 GB
71.0 GB free
241 Ollama Run
Qwen2.5-Coder 7B 7.62B Q5_K_M 5.0 GB 1.75 GB 7.4 GB
71.0 GB free
241 Ollama Run
Olmo 3 7B Instruct 7.3B Q5_K_M 4.8 GB 5.50 GB 10.9 GB
67.5 GB free
251 Ollama Run
Mistral 7B Instruct v0.3 7.25B Q5_K_M 4.8 GB 4.00 GB 9.4 GB
69.0 GB free
253 Ollama Run
Gemma 4 E2B 5.1B Q5_K_M 3.4 GB 0.23 GB 4.2 GB
74.2 GB free
360 Ollama Run
Qwen3.5 4B 4.66B Q5_K_M 3.1 GB 1.00 GB 4.7 GB
73.7 GB free
394 Ollama Run
Gemma 3 4B 4.3B Q5_K_M 2.8 GB 0.86 GB 4.3 GB
74.1 GB free
427 Ollama Run
Qwen3 4B 4.02B Q5_K_M 2.7 GB 4.50 GB 7.8 GB
70.6 GB free
456 Ollama Run
Ministral 3 3B 3.85B Q5_K_M 2.5 GB 3.25 GB 6.4 GB
72.0 GB free
476 Ollama Run
Phi-4-mini 3.8B 3.84B Q5_K_M 2.5 GB 4.00 GB 7.1 GB
71.3 GB free
478 Ollama Run
Granite 4.1 3B 3.4B Q5_K_M 2.2 GB 2.50 GB 5.3 GB
73.1 GB free
539 Ollama Run
Llama 3.2 3B Instruct 3.21B Q5_K_M 2.1 GB 3.50 GB 6.2 GB
72.2 GB free
571 Ollama Run
LFM2.5 2.6B 2.7B Q5_K_M 1.8 GB 0.50 GB 2.9 GB
75.5 GB free
679 llama.cpp Run
Qwen3.5 2B 2.27B Q5_K_M 1.5 GB 0.38 GB 2.5 GB
75.9 GB free
808 Ollama Run
Qwen3 1.7B 1.72B Q5_K_M 1.1 GB 3.50 GB 5.2 GB
73.2 GB free
1066 Ollama Run
Llama 3.2 1B Instruct 1.24B Q5_K_M 0.8 GB 1.00 GB 2.4 GB
76.0 GB free
1479 Ollama Run
Gemma 3 1B 1.0B Q5_K_M 0.7 GB 0.14 GB 1.4 GB
77.0 GB free
1834 Ollama Run
Qwen3.5 0.8B 0.87B Q5_K_M 0.6 GB 0.38 GB 1.5 GB
76.9 GB free
2108 Ollama Run
Qwen3 0.6B 0.6B Q5_K_M 0.4 GB 3.50 GB 4.5 GB
73.9 GB free
3057 Ollama Run

Runs — tight

1 model · fits at 32K, drop context or quant to go longer
ModelParamsQuantWeights +KV 32KTotal VRAM headroom Tok/sRuntime
Llama 4 Scout 109B-A17B 109B MoE / 17B act Q5_K_M 71.9 GB 2.63 GB 75.2 GB
3.2 GB free
41 llama.cpp Run

Won't fit in VRAM

18 models · some are possible with CPU offload
ModelParamsQuantWeights +KV 32KTotal Over budget Tok/sRuntime
Qwen3 235B-A22B 235B MoE / 22B act Q5_K_M 155.1 GB 5.88 GB 161.6 GB +83.2 GB ~1.7 llama.cpp Why
Qwen3.8-Flash-Next 180B-A6B 180B MoE / 6B act Q5_K_M 118.8 GB 0.75 GB 120.2 GB +41.8 GB ~9.5 llama.cpp Why
Qwen3.5 122B-A10B 125B MoE / 10B act Q5_K_M 82.5 GB 0.75 GB 83.9 GB +5.5 GB ~22 llama.cpp Why
Nemotron 3 Super 120B-A12B 124B MoE / 12B act Q5_K_M 81.8 GB 0.25 GB 82.7 GB +4.3 GB ~22 llama.cpp Why
Ling 3.0 Flash 124B-A5B 124B MoE / 5.1B act Q5_K_M 81.8 GB 0.25 GB 82.7 GB +4.3 GB ~51 llama.cpp Why
Mistral Small 4 119B-A6B 119B MoE / 6.5B act Q5_K_M 78.5 GB 0.70 GB 79.9 GB +1.5 GB ~68 llama.cpp Why
Kimi K3 2.8T-A104B 2780B MoE / 104B act Q5_K_M 1835.0 GB 0.84 GB 1836.5 GB +1758.1 GB ~0.2 llama.cpp Why
Qwen3.8 2.4T-A95B 2446B MoE / 95B act Q5_K_M 1614.5 GB 2.88 GB 1618.0 GB +1539.6 GB ~0.2 llama.cpp Why
DeepSeek V4 Pro 1.6T-A49B 1650B MoE / 49B act Q5_K_M 1089.1 GB 2.14 GB 1091.9 GB +1013.5 GB ~0.5 llama.cpp Why
Kimi K2.6 1T-A32B 1027B MoE / 32B act Q5_K_M 677.9 GB 2.14 GB 680.6 GB +602.2 GB ~0.7 llama.cpp Why
GLM-5.2 744B-A40B 753B MoE / 40B act Q5_K_M 497.0 GB 2.74 GB 500.4 GB +422.0 GB ~0.6 llama.cpp Why
GLM-5.3 744B-A40B 753B MoE / 40B act Q5_K_M 497.0 GB 2.74 GB 500.4 GB +422.0 GB ~0.6 llama.cpp Why
DeepSeek-R1 671B 671B MoE / 37B act Q5_K_M 442.9 GB 2.14 GB 445.7 GB +367.3 GB ~0.7 llama.cpp Why
DeepSeek V4.1 Flash 552B-A16B New 552B MoE / 16B act Q5_K_M 364.4 GB 0.15 GB 365.1 GB +286.7 GB ~1.7 vLLM Why
Qwen3.5 397B-A17B 403B MoE / 17B act Q5_K_M 266.0 GB 0.94 GB 267.5 GB +189.1 GB ~1.7 llama.cpp Why
Ornith 1.5 397B-A17B 397B MoE / 17B act Q5_K_M 262.0 GB 0.94 GB 263.6 GB +185.2 GB ~1.7 llama.cpp Why
GLM-5.3-Flash 320B-A18B 321B MoE / 18B act Q5_K_M 211.9 GB 0.34 GB 212.8 GB +134.4 GB ~1.8 llama.cpp Why
DeepSeek V4 Flash 284B-A13B 284B MoE / 13B act Q5_K_M 187.5 GB 1.51 GB 189.6 GB +111.2 GB ~2.7 llama.cpp Why

Totals = quantised weights + f16 KV cache at 32K tokens + 0.6 GB runtime overhead, against 78.4 GB usable VRAM (80 GB less display and driver reserve). Tokens per second are estimated from 2000 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.


Same memory, different speed

These devices have the same 78.4 GB usable, so they run exactly the models above. Generation speed scales with memory bandwidth.

DeviceBandwidthSpeed vs yours
H100 SXM
Hopper · 2022
3350 GB/s 1.68×
A100 80 GB
Ampere · 2021
2039 GB/s 1.02×