Your rig
Instinct MI300X · 192 GB
128 GB system RAM · CDNA 3 · 5300 GB/s · 190.4 GB usable VRAM
Which one should I actually run?
Best models for your Instinct MI300X
What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q8_0 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. | Q8_0 · 28.6 GB | 117 | 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. | Q8_0 · 123.4 GB | 245 | 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. | Q8_0 · 123.4 GB | 245 | 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. | Q8_0 · 73.0 GB | 46 | 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. | Q8_0 · 28.6 GB | 117 | 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. | Q8_0 · 123.4 GB | 245 | 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. | Q8_0 · 28.6 GB | 117 | 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. | Q8_0 · 36.3 GB | 378 | 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. | Q8_0 · 36.1 GB at 128K context |
117 | 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 | Q8_0 | 123.7 GB | 0.19 GB | 124.5 GB |
65.9 GB free
|
125 | Ollama | Run |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q8_0 | 122.7 GB | 0.06 GB | 123.4 GB |
67.0 GB free
|
104 | llama.cpp | Run |
| Ling 3.0 Flash 124B-A5B New | 124B MoE / 5.1B act | Q8_0 | 122.7 GB | 0.06 GB | 123.4 GB |
67.0 GB free
|
245 | llama.cpp | Run |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q8_0 | 117.8 GB | 0.18 GB | 118.5 GB |
71.9 GB free
|
192 | llama.cpp | Run |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 0.29 GB | 61.4 GB |
129.0 GB free
|
467 | Ollama | Run |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q8_0 | 107.9 GB | 1.50 GB | 110.0 GB |
80.4 GB free
|
73 | Ollama | Run |
| Llama 3.3 70B Instruct | 70.6B | Q8_0 | 69.9 GB | 2.50 GB | 73.0 GB |
117.4 GB free
|
46 | Ollama | Run |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q8_0 | 69.9 GB | 2.50 GB | 73.0 GB |
117.4 GB free
|
46 | Ollama | Run |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q8_0 | 35.5 GB | 0.16 GB | 36.3 GB |
154.1 GB free
|
378 | Ollama | Run |
| Ornith 1.5 35B-A3B New this week | 35.9B MoE / 3.3B act | Q8_0 | 35.5 GB | 0.16 GB | 36.3 GB |
154.1 GB free
|
378 | Ollama | Run |
| LLM-jp 4 33B Thinking New this week | 33.2B | Q8_0 | 32.9 GB | 2.00 GB | 35.5 GB |
154.9 GB free
|
98 | llama.cpp | Run |
| Qwen3 32B | 32.8B | Q8_0 | 32.5 GB | 2.00 GB | 35.1 GB |
155.3 GB free
|
99 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q8_0 | 32.5 GB | 2.00 GB | 35.1 GB |
155.3 GB free
|
99 | Ollama | Run |
| Qwen2.5-Coder 32B | 32.8B | Q8_0 | 32.5 GB | 2.00 GB | 35.1 GB |
155.3 GB free
|
99 | Ollama | Run |
| Olmo 3.1 32B Instruct | 32.2B | Q8_0 | 31.9 GB | 1.25 GB | 33.7 GB |
156.7 GB free
|
101 | Ollama | Run |
| Nemotron 3.5 Lightning 30B-A3B New | 31.6B MoE / 3.2B act | Q8_0 | 31.3 GB | 0.05 GB | 31.9 GB |
158.5 GB free
|
390 | Ollama | Run |
| Gemma 4 31B | 31.3B | Q8_0 | 31.0 GB | 2.03 GB | 33.6 GB |
156.8 GB free
|
104 | Ollama | Run |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q8_0 | 30.9 GB | 0.41 GB | 31.9 GB |
158.5 GB free
|
416 | Ollama | Run |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q8_0 | 30.2 GB | 0.75 GB | 31.5 GB |
158.9 GB free
|
378 | Ollama | Run |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q8_0 | 30.2 GB | 0.75 GB | 31.5 GB |
158.9 GB free
|
378 | Ollama | Run |
| Muse Glimmer 30B New | 29.8B | Q8_0 | 29.5 GB | 0.18 GB | 30.3 GB |
160.1 GB free
|
109 | Ollama | Run |
| Granite 4.1 30B | 28.9B | Q8_0 | 28.6 GB | 2.00 GB | 31.2 GB |
159.2 GB free
|
112 | Ollama | Run |
| Qwen3.8 27B New this week | 27.8B | Q8_0 | 27.5 GB | 0.50 GB | 28.6 GB |
161.8 GB free
|
117 | Ollama | Run |
| Qwen3.6 27B | 27.8B | Q8_0 | 27.5 GB | 0.50 GB | 28.6 GB |
161.8 GB free
|
117 | Ollama | Run |
| Gemma 3 27B | 27.4B | Q8_0 | 27.1 GB | 1.03 GB | 28.7 GB |
161.7 GB free
|
118 | Ollama | Run |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q8_0 | 26.2 GB | 0.51 GB | 27.3 GB |
163.1 GB free
|
328 | Ollama | Run |
| Devstral Small 2 24B | 24B | Q8_0 | 23.7 GB | 1.25 GB | 25.6 GB |
164.8 GB free
|
135 | llama.cpp | Run |
| Mistral Small 3.2 24B | 23.6B | Q8_0 | 23.4 GB | 1.25 GB | 25.2 GB |
165.2 GB free
|
137 | Ollama | Run |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 0.19 GB | 11.6 GB |
178.8 GB free
|
662 | Ollama | Run |
| Qwen3 14B | 14.8B | Q8_0 | 14.6 GB | 1.25 GB | 16.5 GB |
173.9 GB free
|
219 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q8_0 | 14.6 GB | 1.50 GB | 16.7 GB |
173.7 GB free
|
219 | Ollama | Run |
| Qwen2.5-Coder 14B | 14.8B | Q8_0 | 14.6 GB | 1.50 GB | 16.7 GB |
173.7 GB free
|
219 | Ollama | Run |
| Phi-4 14B | 14.7B | Q8_0 | 14.5 GB | 1.56 GB | 16.7 GB |
173.7 GB free
|
221 | Ollama | Run |
| Ministral 3 14B | 13.9B | Q8_0 | 13.8 GB | 1.25 GB | 15.6 GB |
174.8 GB free
|
233 | Ollama | Run |
| Gemma 3 12B | 12.2B | Q8_0 | 12.1 GB | 0.81 GB | 13.5 GB |
176.9 GB free
|
266 | Ollama | Run |
| Mistral NeMo 12B | 12.2B | Q8_0 | 12.1 GB | 1.25 GB | 13.9 GB |
176.5 GB free
|
266 | Ollama | Run |
| Gemma 4 12B | 12B | Q8_0 | 11.9 GB | 0.81 GB | 13.3 GB |
177.1 GB free
|
270 | Ollama | Run |
| Qwen3.5 9B | 9.65B | Q8_0 | 9.5 GB | 0.25 GB | 10.4 GB |
180.0 GB free
|
336 | Ollama | Run |
| Ornith 1.5 9B New this week | 9.41B | Q8_0 | 9.3 GB | 0.25 GB | 10.2 GB |
180.2 GB free
|
345 | Ollama | Run |
| Ministral 3 8B | 8.92B | Q8_0 | 8.8 GB | 1.06 GB | 10.5 GB |
179.9 GB free
|
363 | Ollama | Run |
| Granite 4.1 8B | 8.79B | Q8_0 | 8.7 GB | 1.25 GB | 10.5 GB |
179.9 GB free
|
369 | Ollama | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q8_0 | 8.4 GB | 0.09 GB | 9.1 GB |
181.3 GB free
|
831 | Ollama | Run |
| Fara 7B | 8.29B | Q8_0 | 8.2 GB | 0.44 GB | 9.2 GB |
181.2 GB free
|
391 | llama.cpp | Run |
| Qwen3 8B | 8.19B | Q8_0 | 8.1 GB | 1.13 GB | 9.8 GB |
180.6 GB free
|
396 | Ollama | Run |
| Llama 3.1 8B Instruct | 8.03B | Q8_0 | 7.9 GB | 1.00 GB | 9.5 GB |
180.9 GB free
|
404 | Ollama | Run |
| Gemma 4 E4B | 8.0B | Q8_0 | 7.9 GB | 0.14 GB | 8.7 GB |
181.7 GB free
|
405 | Ollama | Run |
| Ling 3.0 Tiny 7.9B-A1.3B New | 7.9B MoE / 1.3B act | Q8_0 | 7.8 GB | 0.05 GB | 8.5 GB |
181.9 GB free
|
959 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q8_0 | 7.5 GB | 0.44 GB | 8.6 GB |
181.8 GB free
|
426 | Ollama | Run |
| Qwen2.5-Coder 7B | 7.62B | Q8_0 | 7.5 GB | 0.44 GB | 8.6 GB |
181.8 GB free
|
426 | Ollama | Run |
| Olmo 3 7B Instruct | 7.3B | Q8_0 | 7.2 GB | 2.50 GB | 10.3 GB |
180.1 GB free
|
444 | Ollama | Run |
| Mistral 7B Instruct v0.3 | 7.25B | Q8_0 | 7.2 GB | 1.00 GB | 8.8 GB |
181.6 GB free
|
447 | Ollama | Run |
| Gemma 4 E2B | 5.1B | Q8_0 | 5.0 GB | 0.07 GB | 5.7 GB |
184.7 GB free
|
636 | Ollama | Run |
| Qwen3.5 4B | 4.66B | Q8_0 | 4.6 GB | 0.25 GB | 5.5 GB |
184.9 GB free
|
696 | Ollama | Run |
| Gemma 3 4B | 4.3B | Q8_0 | 4.3 GB | 0.30 GB | 5.2 GB |
185.2 GB free
|
754 | Ollama | Run |
| Qwen3 4B | 4.02B | Q8_0 | 4.0 GB | 1.13 GB | 5.7 GB |
184.7 GB free
|
807 | Ollama | Run |
| Ministral 3 3B | 3.85B | Q8_0 | 3.8 GB | 0.81 GB | 5.2 GB |
185.2 GB free
|
842 | Ollama | Run |
| Phi-4-mini 3.8B | 3.84B | Q8_0 | 3.8 GB | 1.00 GB | 5.4 GB |
185.0 GB free
|
844 | Ollama | Run |
| Granite 4.1 3B | 3.4B | Q8_0 | 3.4 GB | 0.63 GB | 4.6 GB |
185.8 GB free
|
954 | Ollama | Run |
| Llama 3.2 3B Instruct | 3.21B | Q8_0 | 3.2 GB | 0.88 GB | 4.7 GB |
185.7 GB free
|
1010 | Ollama | Run |
| LFM2.5 2.6B New | 2.7B | Q8_0 | 2.7 GB | 0.13 GB | 3.4 GB |
187.0 GB free
|
1201 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q8_0 | 2.2 GB | 0.09 GB | 2.9 GB |
187.5 GB free
|
1428 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q8_0 | 1.7 GB | 0.88 GB | 3.2 GB |
187.2 GB free
|
1885 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q8_0 | 1.2 GB | 0.25 GB | 2.1 GB |
188.3 GB free
|
2615 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q8_0 | 1.0 GB | 0.04 GB | 1.6 GB |
188.8 GB free
|
3242 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q8_0 | 0.9 GB | 0.09 GB | 1.6 GB |
188.8 GB free
|
3727 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q8_0 | 0.6 GB | 0.88 GB | 2.1 GB |
188.3 GB free
|
5404 | Ollama | Run |
Won't fit in VRAM
10 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 | Q8_0 | 281.0 GB | 0.38 GB | 282.0 GB | +91.6 GB | ~3.3 | llama.cpp | Why |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q8_0 | 232.5 GB | 1.47 GB | 234.6 GB | +44.2 GB | ~3.2 | llama.cpp | Why |
| Kimi K3 2.8T-A104B New | 2780B MoE / 104B act | Q8_0 | 2750.9 GB | 0.21 GB | 2751.7 GB | +2561.3 GB | ~0.1 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B New | 2446B MoE / 95B act | Q8_0 | 2420.4 GB | 0.72 GB | 2421.7 GB | +2231.3 GB | ~0.2 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B New | 1650B MoE / 49B act | Q8_0 | 1632.7 GB | 0.54 GB | 1633.9 GB | +1443.5 GB | ~0.3 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q8_0 | 1016.2 GB | 0.54 GB | 1017.4 GB | +827.0 GB | ~0.5 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q8_0 | 745.1 GB | 0.69 GB | 746.4 GB | +556.0 GB | ~0.5 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q8_0 | 664.0 GB | 0.54 GB | 665.1 GB | +474.7 GB | ~0.5 | llama.cpp | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q8_0 | 398.8 GB | 0.23 GB | 399.6 GB | +209.2 GB | ~1.6 | llama.cpp | Why |
| Ornith 1.5 397B-A17B New this week | 397B MoE / 17B act | Q8_0 | 392.8 GB | 0.23 GB | 393.7 GB | +203.3 GB | ~1.6 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 8K tokens + 0.6 GB runtime overhead, against 190.4 GB usable VRAM (192 GB less display and driver reserve). Tokens per second are estimated from 5300 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.