Your rig
Radeon RX 7900 GRE · 16 GB
128 GB system RAM · RDNA 3 · 576 GB/s · 14.4 GB usable VRAM
Which one should I actually run?
Best models for your Radeon RX 7900 GRE
What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q2_K and 4K. 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. | Q2_K · 11.7 GB | 32 | 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. | Q2_K · 11.7 GB | 32 | Runs great |
| Best reasoning | Qwen3.8 27B New this week Alibaba · Apache 2.0 |
Thinking mode plus the best agentic reasoning at 24 GB. | Q2_K · 11.7 GB | 32 | Runs great |
| Best for writing | Gemma 4 26B-A4B Google · Apache 2.0 |
Gemma 4 prose at MoE speed, with room for a long draft in context. | Q2_K · 11.3 GB | 90 | 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. | Q2_K · 11.7 GB | 32 | 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). | Q2_K · 11.7 GB | 32 | 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. | Q2_K · 11.7 GB | 32 | Runs great |
| Fastest good model | Gemma 4 26B-A4B Google · Apache 2.0 |
3.8B active and a small file — the quickest Gemma 4 with vision. | Q2_K · 11.3 GB | 90 | Runs great |
| Best long context | Nemotron 3.5 Lightning 30B-A3B New NVIDIA · OpenMDW-1.1 |
262K, and a Mamba hybrid whose cache barely grows. | Q2_K · 13.7 GB at 128K context |
107 | Tight fit |
Everything that fits
Runs great
44 of 76 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 4K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 27B New this week | 27.8B | Q2_K | 10.8 GB | 0.25 GB | 11.7 GB |
2.7 GB free
|
32 | Ollama | Run |
| Qwen3.6 27B | 27.8B | Q2_K | 10.8 GB | 0.25 GB | 11.7 GB |
2.7 GB free
|
32 | Ollama | Run |
| Gemma 3 27B | 27.4B | Q2_K | 10.7 GB | 0.72 GB | 12.0 GB |
2.4 GB free
|
33 | Ollama | Run |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q2_K | 10.3 GB | 0.35 GB | 11.3 GB |
3.1 GB free
|
90 | Ollama | Run |
| Devstral Small 2 24B | 24B | Q2_K | 9.4 GB | 0.63 GB | 10.6 GB |
3.8 GB free
|
37 | llama.cpp | Run |
| Mistral Small 3.2 24B | 23.6B | Q2_K | 9.2 GB | 0.63 GB | 10.4 GB |
4.0 GB free
|
38 | Ollama | Run |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 0.10 GB | 11.5 GB |
2.9 GB free
|
72 | Ollama | Run |
| Qwen3 14B | 14.8B | Q2_K | 5.8 GB | 0.63 GB | 7.0 GB |
7.4 GB free
|
60 | Ollama | Run |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q2_K | 5.8 GB | 0.75 GB | 7.1 GB |
7.3 GB free
|
60 | Ollama | Run |
| Qwen2.5-Coder 14B | 14.8B | Q2_K | 5.8 GB | 0.75 GB | 7.1 GB |
7.3 GB free
|
60 | Ollama | Run |
| Phi-4 14B | 14.7B | Q2_K | 5.7 GB | 0.78 GB | 7.1 GB |
7.3 GB free
|
61 | Ollama | Run |
| Ministral 3 14B | 13.9B | Q2_K | 5.4 GB | 0.63 GB | 6.6 GB |
7.8 GB free
|
64 | Ollama | Run |
| Gemma 3 12B | 12.2B | Q2_K | 4.8 GB | 0.56 GB | 5.9 GB |
8.5 GB free
|
73 | Ollama | Run |
| Mistral NeMo 12B | 12.2B | Q2_K | 4.8 GB | 0.63 GB | 6.0 GB |
8.4 GB free
|
73 | Ollama | Run |
| Gemma 4 12B | 12B | Q2_K | 4.7 GB | 0.56 GB | 5.8 GB |
8.6 GB free
|
75 | Ollama | Run |
| Qwen3.5 9B | 9.65B | Q2_K | 3.8 GB | 0.13 GB | 4.5 GB |
9.9 GB free
|
93 | Ollama | Run |
| Ornith 1.5 9B New this week | 9.41B | Q2_K | 3.7 GB | 0.13 GB | 4.4 GB |
10.0 GB free
|
95 | Ollama | Run |
| Ministral 3 8B | 8.92B | Q2_K | 3.5 GB | 0.53 GB | 4.6 GB |
9.8 GB free
|
100 | Ollama | Run |
| Granite 4.1 8B | 8.79B | Q2_K | 3.4 GB | 0.63 GB | 4.7 GB |
9.7 GB free
|
102 | Ollama | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q2_K | 3.3 GB | 0.05 GB | 4.0 GB |
10.4 GB free
|
229 | Ollama | Run |
| Fara 7B | 8.29B | Q2_K | 3.2 GB | 0.22 GB | 4.1 GB |
10.3 GB free
|
108 | llama.cpp | Run |
| Qwen3 8B | 8.19B | Q2_K | 3.2 GB | 0.56 GB | 4.4 GB |
10.0 GB free
|
109 | Ollama | Run |
| Llama 3.1 8B Instruct | 8.03B | Q2_K | 3.1 GB | 0.50 GB | 4.2 GB |
10.2 GB free
|
111 | Ollama | Run |
| Gemma 4 E4B | 8.0B | Q2_K | 3.1 GB | 0.09 GB | 3.8 GB |
10.6 GB free
|
112 | Ollama | Run |
| Ling 3.0 Tiny 7.9B-A1.3B New | 7.9B MoE / 1.3B act | Q2_K | 3.1 GB | 0.03 GB | 3.7 GB |
10.7 GB free
|
265 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q2_K | 3.0 GB | 0.22 GB | 3.8 GB |
10.6 GB free
|
117 | Ollama | Run |
| Qwen2.5-Coder 7B | 7.62B | Q2_K | 3.0 GB | 0.22 GB | 3.8 GB |
10.6 GB free
|
117 | Ollama | Run |
| Olmo 3 7B Instruct | 7.3B | Q2_K | 2.8 GB | 2.00 GB | 5.4 GB |
9.0 GB free
|
122 | Ollama | Run |
| Mistral 7B Instruct v0.3 | 7.25B | Q2_K | 2.8 GB | 0.50 GB | 3.9 GB |
10.5 GB free
|
123 | Ollama | Run |
| Gemma 4 E2B | 5.1B | Q2_K | 2.0 GB | 0.04 GB | 2.6 GB |
11.8 GB free
|
175 | Ollama | Run |
| Qwen3.5 4B | 4.66B | Q2_K | 1.8 GB | 0.13 GB | 2.5 GB |
11.9 GB free
|
192 | Ollama | Run |
| Gemma 3 4B | 4.3B | Q2_K | 1.7 GB | 0.20 GB | 2.5 GB |
11.9 GB free
|
208 | Ollama | Run |
| Qwen3 4B | 4.02B | Q2_K | 1.6 GB | 0.56 GB | 2.7 GB |
11.7 GB free
|
222 | Ollama | Run |
| Ministral 3 3B | 3.85B | Q2_K | 1.5 GB | 0.41 GB | 2.5 GB |
11.9 GB free
|
232 | Ollama | Run |
| Phi-4-mini 3.8B | 3.84B | Q2_K | 1.5 GB | 0.50 GB | 2.6 GB |
11.8 GB free
|
233 | Ollama | Run |
| Granite 4.1 3B | 3.4B | Q2_K | 1.3 GB | 0.31 GB | 2.2 GB |
12.2 GB free
|
263 | Ollama | Run |
| Llama 3.2 3B Instruct | 3.21B | Q2_K | 1.3 GB | 0.44 GB | 2.3 GB |
12.1 GB free
|
279 | Ollama | Run |
| LFM2.5 2.6B New | 2.7B | Q2_K | 1.1 GB | 0.06 GB | 1.7 GB |
12.7 GB free
|
331 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q2_K | 0.9 GB | 0.05 GB | 1.5 GB |
12.9 GB free
|
394 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q2_K | 0.7 GB | 0.44 GB | 1.7 GB |
12.7 GB free
|
520 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q2_K | 0.5 GB | 0.13 GB | 1.2 GB |
13.2 GB free
|
721 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q2_K | 0.4 GB | 0.03 GB | 1.0 GB |
13.4 GB free
|
894 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q2_K | 0.3 GB | 0.05 GB | 1.0 GB |
13.4 GB free
|
1028 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q2_K | 0.2 GB | 0.44 GB | 1.3 GB |
13.1 GB free
|
1490 | Ollama | Run |
Runs — tight
11 models · fits at 4K, drop context or quant to go longer| Model | Params | Quant | Weights | +KV 4K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3 32B | 32.8B | Q2_K | 12.8 GB | 1.00 GB | 14.4 GB |
0.0 GB free
|
27 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q2_K | 12.8 GB | 1.00 GB | 14.4 GB |
0.0 GB free
|
27 | llama.cpp | Run |
| Qwen2.5-Coder 32B | 32.8B | Q2_K | 12.8 GB | 1.00 GB | 14.4 GB |
0.0 GB free
|
27 | llama.cpp | Run |
| Olmo 3.1 32B Instruct | 32.2B | Q2_K | 12.6 GB | 1.00 GB | 14.2 GB |
0.2 GB free
|
28 | llama.cpp | Run |
| Nemotron 3.5 Lightning 30B-A3B New | 31.6B MoE / 3.2B act | Q2_K | 12.3 GB | 0.02 GB | 12.9 GB |
1.5 GB free
|
107 | llama.cpp | Run |
| Gemma 4 31B | 31.3B | Q2_K | 12.2 GB | 1.41 GB | 14.2 GB |
0.2 GB free
|
29 | llama.cpp | Run |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q2_K | 12.2 GB | 0.21 GB | 13.0 GB |
1.4 GB free
|
115 | llama.cpp | Run |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q2_K | 11.9 GB | 0.38 GB | 12.9 GB |
1.5 GB free
|
104 | llama.cpp | Run |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q2_K | 11.9 GB | 0.38 GB | 12.9 GB |
1.5 GB free
|
104 | llama.cpp | Run |
| Muse Glimmer 30B New | 29.8B | Q2_K | 11.6 GB | 0.13 GB | 12.3 GB |
2.1 GB free
|
30 | llama.cpp | Run |
| Granite 4.1 30B | 28.9B | Q2_K | 11.3 GB | 1.00 GB | 12.9 GB |
1.5 GB free
|
31 | llama.cpp | Run |
Won't fit in VRAM
21 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 4K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 284B-A13B New | 284B MoE / 13B act | Q2_K | 110.8 GB | 0.19 GB | 111.5 GB | +97.1 GB | ~3.1 | llama.cpp | Why |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q2_K | 91.6 GB | 0.73 GB | 93.0 GB | +78.6 GB | ~1.9 | llama.cpp | Why |
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q2_K | 48.7 GB | 0.09 GB | 49.4 GB | +35.0 GB | ~4.8 | llama.cpp | Why |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q2_K | 48.4 GB | 0.03 GB | 49.0 GB | +34.6 GB | ~4.0 | llama.cpp | Why |
| Ling 3.0 Flash 124B-A5B New | 124B MoE / 5.1B act | Q2_K | 48.4 GB | 0.03 GB | 49.0 GB | +34.6 GB | ~9.4 | llama.cpp | Why |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q2_K | 46.4 GB | 0.09 GB | 47.1 GB | +32.7 GB | ~7.5 | llama.cpp | Why |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 0.15 GB | 61.3 GB | +46.9 GB | ~6.6 | llama.cpp | Why |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q2_K | 42.5 GB | 0.75 GB | 43.9 GB | +29.5 GB | ~2.9 | llama.cpp | Why |
| Llama 3.3 70B Instruct | 70.6B | Q2_K | 27.5 GB | 1.25 GB | 29.4 GB | +15.0 GB | ~2.2 | llama.cpp | Why |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q2_K | 27.5 GB | 1.25 GB | 29.4 GB | +15.0 GB | ~2.2 | llama.cpp | Why |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q2_K | 14.0 GB | 0.08 GB | 14.7 GB | +0.3 GB | ~89 | llama.cpp | Why |
| Ornith 1.5 35B-A3B New this week | 35.9B MoE / 3.3B act | Q2_K | 14.0 GB | 0.08 GB | 14.7 GB | +0.3 GB | ~89 | llama.cpp | Why |
| LLM-jp 4 33B Thinking New this week | 33.2B | Q2_K | 12.9 GB | 1.00 GB | 14.5 GB | +0.1 GB | ~25 | llama.cpp | Why |
| Kimi K3 2.8T-A104B New | 2780B MoE / 104B act | Q2_K | 1084.2 GB | 0.11 GB | 1084.9 GB | +1070.5 GB | ~0.3 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B New | 2446B MoE / 95B act | Q2_K | 953.9 GB | 0.36 GB | 954.9 GB | +940.5 GB | ~0.4 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B New | 1650B MoE / 49B act | Q2_K | 643.5 GB | 0.27 GB | 644.4 GB | +630.0 GB | ~0.7 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q2_K | 400.5 GB | 0.27 GB | 401.4 GB | +387.0 GB | ~1.2 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q2_K | 293.7 GB | 0.34 GB | 294.6 GB | +280.2 GB | ~0.9 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q2_K | 261.7 GB | 0.27 GB | 262.6 GB | +248.2 GB | ~1.0 | llama.cpp | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q2_K | 157.2 GB | 0.12 GB | 157.9 GB | +143.5 GB | ~2.3 | llama.cpp | Why |
| Ornith 1.5 397B-A17B New this week | 397B MoE / 17B act | Q2_K | 154.8 GB | 0.12 GB | 155.5 GB | +141.1 GB | ~2.3 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 4K tokens + 0.6 GB runtime overhead, against 14.4 GB usable VRAM (16 GB less display and driver reserve). Tokens per second are estimated from 576 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.