Your rig
GeForce RTX 4060 · 8 GB
32 GB system RAM · Ada Lovelace · 272 GB/s · 7.0 GB usable VRAM
Which one should I actually run?
Best models for your GeForce RTX 4060
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 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 | Qwen3.5 2B Alibaba · Apache 2.0 |
Runs on 4 GB, and still multimodal. | Q8_0 · 4.3 GB | 73 | Runs great |
| Best for coding | Qwen3.5 2B Alibaba · Apache 2.0 |
Autocomplete on 4 GB. | Q8_0 · 4.3 GB | 73 | Runs great |
| Best reasoning | Qwen3.5 2B Alibaba · Apache 2.0 |
Reasoning traces on 4 GB; expect long outputs. | Q8_0 · 4.3 GB | 73 | 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. | Q8_0 · 32.0 GB | ~3.9 | CPU offload |
| Best vision | Qwen3.5 2B Alibaba · Apache 2.0 |
Multimodal on 4 GB. | Q8_0 · 4.3 GB | 73 | Runs great |
| Best for agents | Muse Glimmer 30B New Meta · Apache 2.0 |
Distilled specifically for always-on local agent workflows. | Q8_0 · 31.8 GB | ~1.4 | CPU offload |
| Best translation | Qwen3.5 2B Alibaba · Apache 2.0 |
Phrase-level translation on 4 GB. | Q8_0 · 4.3 GB | 73 | Runs great |
| Fastest good model | Qwen3.5 2B Alibaba · Apache 2.0 |
Instant on anything. | Q8_0 · 4.3 GB | 73 | Runs great |
| Best long context | Qwen3.5 2B Alibaba · Apache 2.0 |
Long documents on 4 GB. | Q8_0 · 4.3 GB at 128K context |
73 | Runs great |
Everything that fits
Runs great
7 of 76 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 128K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| LFM2.5 2.6B New | 2.7B | Q8_0 | 2.7 GB | 2.00 GB | 5.3 GB |
1.7 GB free
|
62 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q8_0 | 2.2 GB | 1.50 GB | 4.3 GB |
2.7 GB free
|
73 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q8_0 | 1.7 GB | 3.50 GB | 5.8 GB |
1.2 GB free
|
97 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q8_0 | 1.2 GB | 4.00 GB | 5.8 GB |
1.2 GB free
|
134 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q8_0 | 1.0 GB | 0.14 GB | 1.7 GB |
5.3 GB free
|
166 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q8_0 | 0.9 GB | 1.50 GB | 3.0 GB |
4.0 GB free
|
191 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q8_0 | 0.6 GB | 3.50 GB | 4.7 GB |
2.3 GB free
|
277 | 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 | |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 E2B | 5.1B | Q8_0 | 5.0 GB | 0.89 GB | 6.5 GB |
0.5 GB free
|
33 | llama.cpp | Run |
Won't fit in VRAM
68 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 128K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Nemotron 3.5 Lightning 30B-A3B New | 31.6B MoE / 3.2B act | Q8_0 | 31.3 GB | 0.75 GB | 32.6 GB | +25.6 GB | ~5.1 | llama.cpp | Why |
| Muse Glimmer 30B New | 29.8B | Q8_0 | 29.5 GB | 1.70 GB | 31.8 GB | +24.8 GB | ~1.4 | llama.cpp | Why |
| Gemma 3 27B | 27.4B | Q8_0 | 27.1 GB | 10.41 GB | 38.1 GB | +31.1 GB | ~1.3 | llama.cpp | Why |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q8_0 | 26.2 GB | 5.20 GB | 32.0 GB | +25.0 GB | ~3.9 | llama.cpp | Why |
| Devstral Small 2 24B | 24B | Q8_0 | 23.7 GB | 20.00 GB | 44.3 GB | +37.3 GB | ~1.5 | llama.cpp | Why |
| Mistral Small 3.2 24B | 23.6B | Q8_0 | 23.4 GB | 20.00 GB | 44.0 GB | +37.0 GB | ~1.6 | llama.cpp | Why |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 3.00 GB | 14.4 GB | +7.4 GB | ~9.9 | llama.cpp | Why |
| Qwen3 14B | 14.8B | Q8_0 | 14.6 GB | 20.00 GB | 35.2 GB | +28.2 GB | ~2.5 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q8_0 | 14.6 GB | 24.00 GB | 39.2 GB | +32.2 GB | ~2.5 | llama.cpp | Why |
| Qwen2.5-Coder 14B | 14.8B | Q8_0 | 14.6 GB | 24.00 GB | 39.2 GB | +32.2 GB | ~2.5 | llama.cpp | Why |
| Phi-4 14B | 14.7B | Q8_0 | 14.5 GB | 3.13 GB | 18.3 GB | +11.3 GB | ~3.0 | llama.cpp | Why |
| Ministral 3 14B | 13.9B | Q8_0 | 13.8 GB | 20.00 GB | 34.4 GB | +27.4 GB | ~2.6 | llama.cpp | Why |
| Gemma 3 12B | 12.2B | Q8_0 | 12.1 GB | 8.31 GB | 21.0 GB | +14.0 GB | ~3.0 | llama.cpp | Why |
| Mistral NeMo 12B | 12.2B | Q8_0 | 12.1 GB | 20.00 GB | 32.7 GB | +25.7 GB | ~3.0 | llama.cpp | Why |
| Gemma 4 12B | 12B | Q8_0 | 11.9 GB | 8.31 GB | 20.8 GB | +13.8 GB | ~3.1 | llama.cpp | Why |
| Qwen3.5 9B | 9.65B | Q8_0 | 9.5 GB | 4.00 GB | 14.1 GB | +7.1 GB | ~4.7 | llama.cpp | Why |
| Ornith 1.5 9B New this week | 9.41B | Q8_0 | 9.3 GB | 4.00 GB | 13.9 GB | +6.9 GB | ~4.9 | llama.cpp | Why |
| Ministral 3 8B | 8.92B | Q8_0 | 8.8 GB | 17.00 GB | 26.4 GB | +19.4 GB | ~4.1 | llama.cpp | Why |
| Granite 4.1 8B | 8.79B | Q8_0 | 8.7 GB | 20.00 GB | 29.3 GB | +22.3 GB | ~4.2 | llama.cpp | Why |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q8_0 | 8.4 GB | 1.46 GB | 10.4 GB | +3.4 GB | ~17 | llama.cpp | Why |
| Fara 7B | 8.29B | Q8_0 | 8.2 GB | 6.84 GB | 15.6 GB | +8.6 GB | ~4.4 | llama.cpp | Why |
| Qwen3 8B | 8.19B | Q8_0 | 8.1 GB | 18.00 GB | 26.7 GB | +19.7 GB | ~4.5 | llama.cpp | Why |
| Llama 3.1 8B Instruct | 8.03B | Q8_0 | 7.9 GB | 16.00 GB | 24.5 GB | +17.5 GB | ~4.6 | llama.cpp | Why |
| Gemma 4 E4B | 8.0B | Q8_0 | 7.9 GB | 1.78 GB | 10.3 GB | +3.3 GB | ~8.4 | llama.cpp | Why |
| Ling 3.0 Tiny 7.9B-A1.3B New | 7.9B MoE / 1.3B act | Q8_0 | 7.8 GB | 0.84 GB | 9.3 GB | +2.3 GB | ~24 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q8_0 | 7.5 GB | 7.00 GB | 15.1 GB | +8.1 GB | ~4.8 | llama.cpp | Why |
| Qwen2.5-Coder 7B | 7.62B | Q8_0 | 7.5 GB | 7.00 GB | 15.1 GB | +8.1 GB | ~4.8 | llama.cpp | Why |
| Olmo 3 7B Instruct | 7.3B | Q8_0 | 7.2 GB | 9.50 GB | 17.3 GB | +10.3 GB | ~5.0 | llama.cpp | Why |
| Mistral 7B Instruct v0.3 | 7.25B | Q8_0 | 7.2 GB | 4.00 GB | 11.8 GB | +4.8 GB | ~6.8 | llama.cpp | Why |
| Qwen3.5 4B | 4.66B | Q8_0 | 4.6 GB | 4.00 GB | 9.2 GB | +2.2 GB | ~13 | llama.cpp | Why |
| Gemma 3 4B | 4.3B | Q8_0 | 4.3 GB | 3.11 GB | 8.0 GB | +1.0 GB | ~21 | llama.cpp | Why |
| Qwen3 4B | 4.02B | Q8_0 | 4.0 GB | 4.50 GB | 9.1 GB | +2.1 GB | ~15 | llama.cpp | Why |
| Ministral 3 3B | 3.85B | Q8_0 | 3.8 GB | 13.00 GB | 17.4 GB | +10.4 GB | ~9.5 | llama.cpp | Why |
| Phi-4-mini 3.8B | 3.84B | Q8_0 | 3.8 GB | 16.00 GB | 20.4 GB | +13.4 GB | ~9.6 | llama.cpp | Why |
| Granite 4.1 3B | 3.4B | Q8_0 | 3.4 GB | 10.00 GB | 14.0 GB | +7.0 GB | ~11 | llama.cpp | Why |
| Llama 3.2 3B Instruct | 3.21B | Q8_0 | 3.2 GB | 14.00 GB | 17.8 GB | +10.8 GB | ~11 | llama.cpp | Why |
| Kimi K3 2.8T-A104B New | 2780B MoE / 104B act | Q8_0 | 2750.9 GB | 3.38 GB | 2754.9 GB | +2747.9 GB | ~0.1 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B New | 2446B MoE / 95B act | Q8_0 | 2420.4 GB | 11.50 GB | 2432.5 GB | +2425.5 GB | ~0.1 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B New | 1650B MoE / 49B act | Q8_0 | 1632.7 GB | 8.58 GB | 1641.9 GB | +1634.9 GB | ~0.3 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q8_0 | 1016.2 GB | 8.58 GB | 1025.4 GB | +1018.4 GB | ~0.4 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q8_0 | 745.1 GB | 10.97 GB | 756.7 GB | +749.7 GB | ~0.4 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q8_0 | 664.0 GB | 8.58 GB | 673.2 GB | +666.2 GB | ~0.4 | llama.cpp | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q8_0 | 398.8 GB | 3.75 GB | 403.1 GB | +396.1 GB | ~0.8 | llama.cpp | Why |
| Ornith 1.5 397B-A17B New this week | 397B MoE / 17B act | Q8_0 | 392.8 GB | 3.75 GB | 397.2 GB | +390.2 GB | ~0.8 | llama.cpp | Why |
| DeepSeek V4 Flash 284B-A13B New | 284B MoE / 13B act | Q8_0 | 281.0 GB | 6.05 GB | 287.7 GB | +280.7 GB | ~1.1 | llama.cpp | Why |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q8_0 | 232.5 GB | 23.50 GB | 256.6 GB | +249.6 GB | ~0.6 | llama.cpp | Why |
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q8_0 | 123.7 GB | 3.00 GB | 127.3 GB | +120.3 GB | ~1.4 | llama.cpp | Why |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q8_0 | 122.7 GB | 1.00 GB | 124.3 GB | +117.3 GB | ~1.2 | llama.cpp | Why |
| Ling 3.0 Flash 124B-A5B New | 124B MoE / 5.1B act | Q8_0 | 122.7 GB | 0.98 GB | 124.3 GB | +117.3 GB | ~2.9 | llama.cpp | Why |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q8_0 | 117.8 GB | 2.81 GB | 121.2 GB | +114.2 GB | ~2.2 | llama.cpp | Why |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 4.50 GB | 65.6 GB | +58.6 GB | ~5.4 | llama.cpp | Why |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q8_0 | 107.9 GB | 7.13 GB | 115.6 GB | +108.6 GB | ~0.8 | llama.cpp | Why |
| Llama 3.3 70B Instruct | 70.6B | Q8_0 | 69.9 GB | 40.00 GB | 110.5 GB | +103.5 GB | ~0.5 | llama.cpp | Why |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q8_0 | 69.9 GB | 40.00 GB | 110.5 GB | +103.5 GB | ~0.5 | llama.cpp | Why |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q8_0 | 35.5 GB | 2.50 GB | 38.6 GB | +31.6 GB | ~4.7 | llama.cpp | Why |
| Ornith 1.5 35B-A3B New this week | 35.9B MoE / 3.3B act | Q8_0 | 35.5 GB | 2.50 GB | 38.6 GB | +31.6 GB | ~4.7 | llama.cpp | Why |
| LLM-jp 4 33B Thinking New this week | 33.2B | Q8_0 | 32.9 GB | 16.00 GB | 49.5 GB | +42.5 GB | ~1.1 | llama.cpp | Why |
| Qwen3 32B | 32.8B | Q8_0 | 32.5 GB | 32.00 GB | 65.1 GB | +58.1 GB | ~1.1 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q8_0 | 32.5 GB | 32.00 GB | 65.1 GB | +58.1 GB | ~1.1 | llama.cpp | Why |
| Qwen2.5-Coder 32B | 32.8B | Q8_0 | 32.5 GB | 32.00 GB | 65.1 GB | +58.1 GB | ~1.1 | llama.cpp | Why |
| Olmo 3.1 32B Instruct | 32.2B | Q8_0 | 31.9 GB | 4.75 GB | 37.2 GB | +30.2 GB | ~1.2 | llama.cpp | Why |
| Gemma 4 31B | 31.3B | Q8_0 | 31.0 GB | 20.78 GB | 52.4 GB | +45.4 GB | ~1.2 | llama.cpp | Why |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q8_0 | 30.9 GB | 6.61 GB | 38.1 GB | +31.1 GB | ~4.7 | llama.cpp | Why |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q8_0 | 30.2 GB | 12.00 GB | 42.8 GB | +35.8 GB | ~4.3 | llama.cpp | Why |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q8_0 | 30.2 GB | 12.00 GB | 42.8 GB | +35.8 GB | ~4.3 | llama.cpp | Why |
| Granite 4.1 30B | 28.9B | Q8_0 | 28.6 GB | 32.00 GB | 61.2 GB | +54.2 GB | ~1.3 | llama.cpp | Why |
| Qwen3.8 27B New this week | 27.8B | Q8_0 | 27.5 GB | 8.00 GB | 36.1 GB | +29.1 GB | ~1.3 | llama.cpp | Why |
| Qwen3.6 27B | 27.8B | Q8_0 | 27.5 GB | 8.00 GB | 36.1 GB | +29.1 GB | ~1.3 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 128K tokens + 0.6 GB runtime overhead, against 7.0 GB usable VRAM (8 GB less display and driver reserve). Tokens per second are estimated from 272 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.