Your rig
Instinct MI300X · 192 GB
32 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 Q4_K_M and 128K. 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 · 24.2 GB | 205 | 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 · 71.3 GB | 430 | 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 · 71.3 GB | 430 | 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 · 80.3 GB | 81 | 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 · 24.2 GB | 205 | 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 · 71.3 GB | 430 | 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 · 24.2 GB | 205 | 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 · 23.3 GB | 665 | 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 |
205 | Runs great |
Everything that fits
Runs great
67 of 76 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 128K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3 235B-A22B | 235B MoE / 22B act | Q4_K_M | 132.1 GB | 23.50 GB | 156.2 GB |
34.2 GB free
|
100 | Ollama | Run |
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q4_K_M | 70.3 GB | 3.00 GB | 73.9 GB |
116.5 GB free
|
219 | Ollama | Run |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q4_K_M | 69.7 GB | 1.00 GB | 71.3 GB |
119.1 GB free
|
183 | llama.cpp | Run |
| Ling 3.0 Flash 124B-A5B New | 124B MoE / 5.1B act | Q4_K_M | 69.7 GB | 0.98 GB | 71.3 GB |
119.1 GB free
|
430 | llama.cpp | Run |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q4_K_M | 66.9 GB | 2.81 GB | 70.3 GB |
120.1 GB free
|
338 | llama.cpp | Run |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 4.50 GB | 65.6 GB |
124.8 GB free
|
467 | Ollama | Run |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q4_K_M | 61.3 GB | 7.13 GB | 69.0 GB |
121.4 GB free
|
129 | Ollama | Run |
| Llama 3.3 70B Instruct | 70.6B | Q4_K_M | 39.7 GB | 40.00 GB | 80.3 GB |
110.1 GB free
|
81 | Ollama | Run |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q4_K_M | 39.7 GB | 40.00 GB | 80.3 GB |
110.1 GB free
|
81 | Ollama | Run |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q4_K_M | 20.2 GB | 2.50 GB | 23.3 GB |
167.1 GB free
|
665 | Ollama | Run |
| Ornith 1.5 35B-A3B New this week | 35.9B MoE / 3.3B act | Q4_K_M | 20.2 GB | 2.50 GB | 23.3 GB |
167.1 GB free
|
665 | Ollama | Run |
| LLM-jp 4 33B Thinking New this week | 33.2B | Q4_K_M | 18.7 GB | 16.00 GB | 35.3 GB |
155.1 GB free
|
172 | llama.cpp | Run |
| Qwen3 32B | 32.8B | Q4_K_M | 18.4 GB | 32.00 GB | 51.0 GB |
139.4 GB free
|
174 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q4_K_M | 18.4 GB | 32.00 GB | 51.0 GB |
139.4 GB free
|
174 | Ollama | Run |
| Qwen2.5-Coder 32B | 32.8B | Q4_K_M | 18.4 GB | 32.00 GB | 51.0 GB |
139.4 GB free
|
174 | Ollama | Run |
| Olmo 3.1 32B Instruct | 32.2B | Q4_K_M | 18.1 GB | 4.75 GB | 23.5 GB |
166.9 GB free
|
177 | Ollama | Run |
| Nemotron 3.5 Lightning 30B-A3B New | 31.6B MoE / 3.2B act | Q4_K_M | 17.8 GB | 0.75 GB | 19.1 GB |
171.3 GB free
|
686 | Ollama | Run |
| Gemma 4 31B | 31.3B | Q4_K_M | 17.6 GB | 20.78 GB | 39.0 GB |
151.4 GB free
|
182 | Ollama | Run |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q4_K_M | 17.5 GB | 6.61 GB | 24.8 GB |
165.6 GB free
|
732 | Ollama | Run |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q4_K_M | 17.1 GB | 12.00 GB | 29.7 GB |
160.7 GB free
|
665 | Ollama | Run |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q4_K_M | 17.1 GB | 12.00 GB | 29.7 GB |
160.7 GB free
|
665 | Ollama | Run |
| Muse Glimmer 30B New | 29.8B | Q4_K_M | 16.8 GB | 1.70 GB | 19.1 GB |
171.3 GB free
|
191 | Ollama | Run |
| Granite 4.1 30B | 28.9B | Q4_K_M | 16.3 GB | 32.00 GB | 48.9 GB |
141.5 GB free
|
197 | Ollama | Run |
| Qwen3.8 27B New this week | 27.8B | Q4_K_M | 15.6 GB | 8.00 GB | 24.2 GB |
166.2 GB free
|
205 | Ollama | Run |
| Qwen3.6 27B | 27.8B | Q4_K_M | 15.6 GB | 8.00 GB | 24.2 GB |
166.2 GB free
|
205 | Ollama | Run |
| Gemma 3 27B | 27.4B | Q4_K_M | 15.4 GB | 10.41 GB | 26.4 GB |
164.0 GB free
|
208 | Ollama | Run |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q4_K_M | 14.9 GB | 5.20 GB | 20.7 GB |
169.7 GB free
|
578 | Ollama | Run |
| Devstral Small 2 24B | 24B | Q4_K_M | 13.5 GB | 20.00 GB | 34.1 GB |
156.3 GB free
|
238 | llama.cpp | Run |
| Mistral Small 3.2 24B | 23.6B | Q4_K_M | 13.3 GB | 20.00 GB | 33.9 GB |
156.5 GB free
|
242 | Ollama | Run |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 3.00 GB | 14.4 GB |
176.0 GB free
|
662 | Ollama | Run |
| Qwen3 14B | 14.8B | Q4_K_M | 8.3 GB | 20.00 GB | 28.9 GB |
161.5 GB free
|
386 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q4_K_M | 8.3 GB | 24.00 GB | 32.9 GB |
157.5 GB free
|
386 | Ollama | Run |
| Qwen2.5-Coder 14B | 14.8B | Q4_K_M | 8.3 GB | 24.00 GB | 32.9 GB |
157.5 GB free
|
386 | Ollama | Run |
| Phi-4 14B | 14.7B | Q4_K_M | 8.3 GB | 3.13 GB | 12.0 GB |
178.4 GB free
|
388 | Ollama | Run |
| Ministral 3 14B | 13.9B | Q4_K_M | 7.8 GB | 20.00 GB | 28.4 GB |
162.0 GB free
|
411 | Ollama | Run |
| Gemma 3 12B | 12.2B | Q4_K_M | 6.9 GB | 8.31 GB | 15.8 GB |
174.6 GB free
|
468 | Ollama | Run |
| Mistral NeMo 12B | 12.2B | Q4_K_M | 6.9 GB | 20.00 GB | 27.5 GB |
162.9 GB free
|
468 | Ollama | Run |
| Gemma 4 12B | 12B | Q4_K_M | 6.7 GB | 8.31 GB | 15.7 GB |
174.7 GB free
|
476 | Ollama | Run |
| Qwen3.5 9B | 9.65B | Q4_K_M | 5.4 GB | 4.00 GB | 10.0 GB |
180.4 GB free
|
591 | Ollama | Run |
| Ornith 1.5 9B New this week | 9.41B | Q4_K_M | 5.3 GB | 4.00 GB | 9.9 GB |
180.5 GB free
|
606 | Ollama | Run |
| Ministral 3 8B | 8.92B | Q4_K_M | 5.0 GB | 17.00 GB | 22.6 GB |
167.8 GB free
|
640 | Ollama | Run |
| Granite 4.1 8B | 8.79B | Q4_K_M | 4.9 GB | 20.00 GB | 25.5 GB |
164.9 GB free
|
649 | Ollama | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q4_K_M | 4.8 GB | 1.46 GB | 6.8 GB |
183.6 GB free
|
1463 | Ollama | Run |
| Fara 7B | 8.29B | Q4_K_M | 4.7 GB | 6.84 GB | 12.1 GB |
178.3 GB free
|
688 | llama.cpp | Run |
| Qwen3 8B | 8.19B | Q4_K_M | 4.6 GB | 18.00 GB | 23.2 GB |
167.2 GB free
|
697 | Ollama | Run |
| Llama 3.1 8B Instruct | 8.03B | Q4_K_M | 4.5 GB | 16.00 GB | 21.1 GB |
169.3 GB free
|
711 | Ollama | Run |
| Gemma 4 E4B | 8.0B | Q4_K_M | 4.5 GB | 1.78 GB | 6.9 GB |
183.5 GB free
|
713 | Ollama | Run |
| Ling 3.0 Tiny 7.9B-A1.3B New | 7.9B MoE / 1.3B act | Q4_K_M | 4.4 GB | 0.84 GB | 5.9 GB |
184.5 GB free
|
1688 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q4_K_M | 4.3 GB | 7.00 GB | 11.9 GB |
178.5 GB free
|
749 | Ollama | Run |
| Qwen2.5-Coder 7B | 7.62B | Q4_K_M | 4.3 GB | 7.00 GB | 11.9 GB |
178.5 GB free
|
749 | Ollama | Run |
| Olmo 3 7B Instruct | 7.3B | Q4_K_M | 4.1 GB | 9.50 GB | 14.2 GB |
176.2 GB free
|
782 | Ollama | Run |
| Mistral 7B Instruct v0.3 | 7.25B | Q4_K_M | 4.1 GB | 4.00 GB | 8.7 GB |
181.7 GB free
|
787 | Ollama | Run |
| Gemma 4 E2B | 5.1B | Q4_K_M | 2.9 GB | 0.89 GB | 4.4 GB |
186.0 GB free
|
1119 | Ollama | Run |
| Qwen3.5 4B | 4.66B | Q4_K_M | 2.6 GB | 4.00 GB | 7.2 GB |
183.2 GB free
|
1224 | Ollama | Run |
| Gemma 3 4B | 4.3B | Q4_K_M | 2.4 GB | 3.11 GB | 6.1 GB |
184.3 GB free
|
1327 | Ollama | Run |
| Qwen3 4B | 4.02B | Q4_K_M | 2.3 GB | 4.50 GB | 7.4 GB |
183.0 GB free
|
1419 | Ollama | Run |
| Ministral 3 3B | 3.85B | Q4_K_M | 2.2 GB | 13.00 GB | 15.8 GB |
174.6 GB free
|
1482 | Ollama | Run |
| Phi-4-mini 3.8B | 3.84B | Q4_K_M | 2.2 GB | 16.00 GB | 18.8 GB |
171.6 GB free
|
1486 | Ollama | Run |
| Granite 4.1 3B | 3.4B | Q4_K_M | 1.9 GB | 10.00 GB | 12.5 GB |
177.9 GB free
|
1678 | Ollama | Run |
| Llama 3.2 3B Instruct | 3.21B | Q4_K_M | 1.8 GB | 14.00 GB | 16.4 GB |
174.0 GB free
|
1778 | Ollama | Run |
| LFM2.5 2.6B New | 2.7B | Q4_K_M | 1.5 GB | 2.00 GB | 4.1 GB |
186.3 GB free
|
2113 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q4_K_M | 1.3 GB | 1.50 GB | 3.4 GB |
187.0 GB free
|
2514 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q4_K_M | 1.0 GB | 3.50 GB | 5.1 GB |
185.3 GB free
|
3317 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q4_K_M | 0.7 GB | 4.00 GB | 5.3 GB |
185.1 GB free
|
4602 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q4_K_M | 0.6 GB | 0.14 GB | 1.3 GB |
189.1 GB free
|
5706 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q4_K_M | 0.5 GB | 1.50 GB | 2.6 GB |
187.8 GB free
|
6559 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q4_K_M | 0.3 GB | 3.50 GB | 4.4 GB |
186.0 GB free
|
9510 | Ollama | Run |
Runs — tight
1 model · fits at 128K, drop context or quant to go longer| Model | Params | Quant | Weights | +KV 128K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 284B-A13B New | 284B MoE / 13B act | Q4_K_M | 159.7 GB | 6.05 GB | 166.3 GB |
24.1 GB free
|
169 | llama.cpp | Run |
Won't fit in VRAM
8 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 128K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 2.8T-A104B New | 2780B MoE / 104B act | Q4_K_M | 1563.2 GB | 3.38 GB | 1567.1 GB | +1376.7 GB | ~0.3 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B New | 2446B MoE / 95B act | Q4_K_M | 1375.4 GB | 11.50 GB | 1387.5 GB | +1197.1 GB | ~0.3 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B New | 1650B MoE / 49B act | Q4_K_M | 927.8 GB | 8.58 GB | 937.0 GB | +746.6 GB | ~0.6 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q4_K_M | 577.5 GB | 8.58 GB | 586.6 GB | +396.2 GB | ~1.1 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q4_K_M | 423.4 GB | 10.97 GB | 435.0 GB | +244.6 GB | ~1.1 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q4_K_M | 377.3 GB | 8.58 GB | 386.5 GB | +196.1 GB | ~1.3 | llama.cpp | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q4_K_M | 226.6 GB | 3.75 GB | 231.0 GB | +40.6 GB | ~7.8 | llama.cpp | Why |
| Ornith 1.5 397B-A17B New this week | 397B MoE / 17B act | Q4_K_M | 223.2 GB | 3.75 GB | 227.6 GB | +37.2 GB | ~8.3 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 128K 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.