Your rig
RTX 4000 Ada · 20 GB
8 GB system RAM · Ada Lovelace · 360 GB/s · 18.4 GB usable VRAM
Which one should I actually run?
Best models for your RTX 4000 Ada
What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q3_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 | Gemma 4 12B Google · Apache 2.0 |
The 12 GB generalist: text, image and audio in, 140+ languages. | Q3_K_M · 14.4 GB | 40 | Runs great |
| Best for coding | Qwen3.5 9B Alibaba · Apache 2.0 |
The best coding model for 8–12 GB cards. | Q3_K_M · 9.0 GB | 50 | Runs great |
| Best reasoning | gpt-oss 20B OpenAI · Apache 2.0 |
Low/medium/high reasoning effort in 13 GB. | MXFP4 · 14.4 GB | 45 | Runs great |
| Best for writing | Gemma 4 12B Google · Apache 2.0 |
The 12 GB writing pick; 140+ languages. | Q3_K_M · 14.4 GB | 40 | Runs great |
| Best vision | Gemma 4 26B-A4B Google · Apache 2.0 |
Vision at MoE speed in 18 GB. | Q3_K_M · 17.9 GB | 48 | Tight fit |
| Best for agents | Muse Glimmer 30B New Meta · Apache 2.0 |
Distilled specifically for always-on local agent workflows. | Q3_K_M · 15.9 GB | 16 | Tight fit |
| Best translation | Gemma 4 12B Google · Apache 2.0 |
Broad language coverage on a 12 GB card. | Q3_K_M · 14.4 GB | 40 | 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. | Q3_K_M · 17.9 GB | 48 | Tight fit |
| Best long context | Nemotron 3.5 Lightning 30B-A3B New NVIDIA · OpenMDW-1.1 |
262K, and a Mamba hybrid whose cache barely grows. | Q3_K_M · 15.7 GB at 128K context |
58 | Tight fit |
Everything that fits
Runs great
27 of 76 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 128K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 3.00 GB | 14.4 GB |
4.0 GB free
|
45 | Ollama | Run |
| Phi-4 14B | 14.7B | Q3_K_M | 6.7 GB | 3.13 GB | 10.4 GB |
8.0 GB free
|
33 | Ollama | Run |
| Gemma 3 12B | 12.2B | Q3_K_M | 5.6 GB | 8.31 GB | 14.5 GB |
3.9 GB free
|
39 | Ollama | Run |
| Gemma 4 12B | 12B | Q3_K_M | 5.5 GB | 8.31 GB | 14.4 GB |
4.0 GB free
|
40 | Ollama | Run |
| Qwen3.5 9B | 9.65B | Q3_K_M | 4.4 GB | 4.00 GB | 9.0 GB |
9.4 GB free
|
50 | Ollama | Run |
| Ornith 1.5 9B New this week | 9.41B | Q3_K_M | 4.3 GB | 4.00 GB | 8.9 GB |
9.5 GB free
|
51 | Ollama | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q3_K_M | 3.9 GB | 1.46 GB | 5.9 GB |
12.5 GB free
|
123 | Ollama | Run |
| Fara 7B | 8.29B | Q3_K_M | 3.8 GB | 6.84 GB | 11.2 GB |
7.2 GB free
|
58 | llama.cpp | Run |
| Gemma 4 E4B | 8.0B | Q3_K_M | 3.6 GB | 1.78 GB | 6.0 GB |
12.4 GB free
|
60 | Ollama | Run |
| Ling 3.0 Tiny 7.9B-A1.3B New | 7.9B MoE / 1.3B act | Q3_K_M | 3.6 GB | 0.84 GB | 5.0 GB |
13.4 GB free
|
142 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q3_K_M | 3.5 GB | 7.00 GB | 11.1 GB |
7.3 GB free
|
63 | Ollama | Run |
| Qwen2.5-Coder 7B | 7.62B | Q3_K_M | 3.5 GB | 7.00 GB | 11.1 GB |
7.3 GB free
|
63 | Ollama | Run |
| Olmo 3 7B Instruct | 7.3B | Q3_K_M | 3.3 GB | 9.50 GB | 13.4 GB |
5.0 GB free
|
66 | Ollama | Run |
| Mistral 7B Instruct v0.3 | 7.25B | Q3_K_M | 3.3 GB | 4.00 GB | 7.9 GB |
10.5 GB free
|
66 | Ollama | Run |
| Gemma 4 E2B | 5.1B | Q3_K_M | 2.3 GB | 0.89 GB | 3.8 GB |
14.6 GB free
|
94 | Ollama | Run |
| Qwen3.5 4B | 4.66B | Q3_K_M | 2.1 GB | 4.00 GB | 6.7 GB |
11.7 GB free
|
103 | Ollama | Run |
| Gemma 3 4B | 4.3B | Q3_K_M | 2.0 GB | 3.11 GB | 5.7 GB |
12.7 GB free
|
111 | Ollama | Run |
| Qwen3 4B | 4.02B | Q3_K_M | 1.8 GB | 4.50 GB | 6.9 GB |
11.5 GB free
|
119 | Ollama | Run |
| Ministral 3 3B | 3.85B | Q3_K_M | 1.8 GB | 13.00 GB | 15.4 GB |
3.0 GB free
|
124 | Ollama | Run |
| Granite 4.1 3B | 3.4B | Q3_K_M | 1.5 GB | 10.00 GB | 12.1 GB |
6.3 GB free
|
141 | Ollama | Run |
| LFM2.5 2.6B New | 2.7B | Q3_K_M | 1.2 GB | 2.00 GB | 3.8 GB |
14.6 GB free
|
177 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q3_K_M | 1.0 GB | 1.50 GB | 3.1 GB |
15.3 GB free
|
211 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q3_K_M | 0.8 GB | 3.50 GB | 4.9 GB |
13.5 GB free
|
278 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q3_K_M | 0.6 GB | 4.00 GB | 5.2 GB |
13.2 GB free
|
386 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q3_K_M | 0.5 GB | 0.14 GB | 1.2 GB |
17.2 GB free
|
479 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q3_K_M | 0.4 GB | 1.50 GB | 2.5 GB |
15.9 GB free
|
550 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q3_K_M | 0.3 GB | 3.50 GB | 4.4 GB |
14.0 GB free
|
798 | Ollama | Run |
Runs — tight
5 models · fits at 128K, drop context or quant to go longer| Model | Params | Quant | Weights | +KV 128K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Nemotron 3.5 Lightning 30B-A3B New | 31.6B MoE / 3.2B act | Q3_K_M | 14.4 GB | 0.75 GB | 15.7 GB |
2.7 GB free
|
58 | llama.cpp | Run |
| Muse Glimmer 30B New | 29.8B | Q3_K_M | 13.6 GB | 1.70 GB | 15.9 GB |
2.5 GB free
|
16 | llama.cpp | Run |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q3_K_M | 12.1 GB | 5.20 GB | 17.9 GB |
0.5 GB free
|
48 | llama.cpp | Run |
| Phi-4-mini 3.8B | 3.84B | Q3_K_M | 1.7 GB | 16.00 GB | 18.3 GB |
0.1 GB free
|
125 | llama.cpp | Run |
| Llama 3.2 3B Instruct | 3.21B | Q3_K_M | 1.5 GB | 14.00 GB | 16.1 GB |
2.3 GB free
|
149 | llama.cpp | Run |
Won't fit in VRAM
44 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 128K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q3_K_M | 16.3 GB | 2.50 GB | 19.4 GB | +1.0 GB | ~42 | llama.cpp | Why |
| Ornith 1.5 35B-A3B New this week | 35.9B MoE / 3.3B act | Q3_K_M | 16.3 GB | 2.50 GB | 19.4 GB | +1.0 GB | ~42 | llama.cpp | Why |
| Olmo 3.1 32B Instruct | 32.2B | Q3_K_M | 14.7 GB | 4.75 GB | 20.0 GB | +1.6 GB | ~9.6 | llama.cpp | Why |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q3_K_M | 14.2 GB | 6.61 GB | 21.4 GB | +3.0 GB | ~30 | llama.cpp | Why |
| Qwen3.8 27B New this week | 27.8B | Q3_K_M | 12.7 GB | 8.00 GB | 21.3 GB | +2.9 GB | ~8.1 | llama.cpp | Why |
| Qwen3.6 27B | 27.8B | Q3_K_M | 12.7 GB | 8.00 GB | 21.3 GB | +2.9 GB | ~8.1 | llama.cpp | Why |
| Gemma 3 27B | 27.4B | Q3_K_M | 12.5 GB | 10.41 GB | 23.5 GB | +5.1 GB | ~5.8 | llama.cpp | Why |
| Qwen3 14B | 14.8B | Q3_K_M | 6.7 GB | 20.00 GB | 27.3 GB | +8.9 GB | ~5.4 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q3_K_M | 6.7 GB | 24.00 GB | 31.3 GB | +12.9 GB | ~5.4 | llama.cpp | Why |
| Qwen2.5-Coder 14B | 14.8B | Q3_K_M | 6.7 GB | 24.00 GB | 31.3 GB | +12.9 GB | ~5.4 | llama.cpp | Why |
| Ministral 3 14B | 13.9B | Q3_K_M | 6.3 GB | 20.00 GB | 26.9 GB | +8.5 GB | ~5.7 | llama.cpp | Why |
| Mistral NeMo 12B | 12.2B | Q3_K_M | 5.6 GB | 20.00 GB | 26.2 GB | +7.8 GB | ~6.5 | llama.cpp | Why |
| Ministral 3 8B | 8.92B | Q3_K_M | 4.1 GB | 17.00 GB | 21.7 GB | +3.3 GB | ~11 | llama.cpp | Why |
| Granite 4.1 8B | 8.79B | Q3_K_M | 4.0 GB | 20.00 GB | 24.6 GB | +6.2 GB | ~9.1 | llama.cpp | Why |
| Qwen3 8B | 8.19B | Q3_K_M | 3.7 GB | 18.00 GB | 22.3 GB | +3.9 GB | ~9.7 | llama.cpp | Why |
| Llama 3.1 8B Instruct | 8.03B | Q3_K_M | 3.7 GB | 16.00 GB | 20.3 GB | +1.9 GB | ~17 | llama.cpp | Why |
| Kimi K3 2.8T-A104B New | 2780B MoE / 104B act | Q3_K_M | 1265.4 GB | 3.38 GB | 1269.4 GB | +1251.0 GB | ~0.3 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B New | 2446B MoE / 95B act | Q3_K_M | 1113.4 GB | 11.50 GB | 1125.5 GB | +1107.1 GB | ~0.3 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B New | 1650B MoE / 49B act | Q3_K_M | 751.1 GB | 8.58 GB | 760.2 GB | +741.8 GB | ~0.6 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q3_K_M | 467.5 GB | 8.58 GB | 476.7 GB | +458.3 GB | ~1.0 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q3_K_M | 342.8 GB | 10.97 GB | 354.3 GB | +335.9 GB | ~0.8 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q3_K_M | 305.4 GB | 8.58 GB | 314.6 GB | +296.2 GB | ~0.9 | llama.cpp | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q3_K_M | 183.4 GB | 3.75 GB | 187.8 GB | +169.4 GB | ~1.9 | llama.cpp | Why |
| Ornith 1.5 397B-A17B New this week | 397B MoE / 17B act | Q3_K_M | 180.7 GB | 3.75 GB | 185.1 GB | +166.7 GB | ~1.9 | llama.cpp | Why |
| DeepSeek V4 Flash 284B-A13B New | 284B MoE / 13B act | Q3_K_M | 129.3 GB | 6.05 GB | 135.9 GB | +117.5 GB | ~2.6 | llama.cpp | Why |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q3_K_M | 107.0 GB | 23.50 GB | 131.1 GB | +112.7 GB | ~1.4 | llama.cpp | Why |
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q3_K_M | 56.9 GB | 3.00 GB | 60.5 GB | +42.1 GB | ~3.9 | llama.cpp | Why |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q3_K_M | 56.4 GB | 1.00 GB | 58.0 GB | +39.6 GB | ~3.4 | llama.cpp | Why |
| Ling 3.0 Flash 124B-A5B New | 124B MoE / 5.1B act | Q3_K_M | 56.4 GB | 0.98 GB | 58.0 GB | +39.6 GB | ~8.0 | llama.cpp | Why |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q3_K_M | 54.2 GB | 2.81 GB | 57.6 GB | +39.2 GB | ~6.1 | llama.cpp | Why |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 4.50 GB | 65.6 GB | +47.2 GB | ~6.5 | llama.cpp | Why |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q3_K_M | 49.6 GB | 7.13 GB | 57.3 GB | +38.9 GB | ~2.2 | llama.cpp | Why |
| Llama 3.3 70B Instruct | 70.6B | Q3_K_M | 32.1 GB | 40.00 GB | 72.7 GB | +54.3 GB | ~1.1 | llama.cpp | Why |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q3_K_M | 32.1 GB | 40.00 GB | 72.7 GB | +54.3 GB | ~1.1 | llama.cpp | Why |
| LLM-jp 4 33B Thinking New this week | 33.2B | Q3_K_M | 15.1 GB | 16.00 GB | 31.7 GB | +13.3 GB | ~2.7 | llama.cpp | Why |
| Qwen3 32B | 32.8B | Q3_K_M | 14.9 GB | 32.00 GB | 47.5 GB | +29.1 GB | ~2.4 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q3_K_M | 14.9 GB | 32.00 GB | 47.5 GB | +29.1 GB | ~2.4 | llama.cpp | Why |
| Qwen2.5-Coder 32B | 32.8B | Q3_K_M | 14.9 GB | 32.00 GB | 47.5 GB | +29.1 GB | ~2.4 | llama.cpp | Why |
| Gemma 4 31B | 31.3B | Q3_K_M | 14.2 GB | 20.78 GB | 35.6 GB | +17.2 GB | ~2.5 | llama.cpp | Why |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q3_K_M | 13.9 GB | 12.00 GB | 26.5 GB | +8.1 GB | ~14 | llama.cpp | Why |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q3_K_M | 13.9 GB | 12.00 GB | 26.5 GB | +8.1 GB | ~14 | llama.cpp | Why |
| Granite 4.1 30B | 28.9B | Q3_K_M | 13.2 GB | 32.00 GB | 45.8 GB | +27.4 GB | ~2.8 | llama.cpp | Why |
| Devstral Small 2 24B | 24B | Q3_K_M | 10.9 GB | 20.00 GB | 31.5 GB | +13.1 GB | ~3.3 | llama.cpp | Why |
| Mistral Small 3.2 24B | 23.6B | Q3_K_M | 10.7 GB | 20.00 GB | 31.3 GB | +12.9 GB | ~3.4 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 128K tokens + 0.6 GB runtime overhead, against 18.4 GB usable VRAM (20 GB less display and driver reserve). Tokens per second are estimated from 360 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.