Your rig
GeForce RTX 2060 12 GB · 12 GB
Which one should I actually run?
Best models for your GeForce RTX 2060 12 GB
What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q5_K_M and 8K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.
| Recommendation | Model | Why | Quant · total | Tok/s est. | |
|---|---|---|---|---|---|
| Best overall | Qwen3.5 9B Alibaba · Apache 2.0 |
The 8–12 GB default of 2026 — beats every older 8B, with vision. | Q5_K_M · 7.2 GB | 32 | Runs great |
| Best for coding | Qwen3.5 9B Alibaba · Apache 2.0 |
The best coding model for 8–12 GB cards. | Q5_K_M · 7.2 GB | 32 | Runs great |
| Best reasoning | Qwen3.5 9B Alibaba · Apache 2.0 |
Thinking mode on a 12 GB card — ahead of the 2025 R1 distills. | Q5_K_M · 7.2 GB | 32 | Runs great |
| Best for writing | Ministral 3 8B Mistral AI · Apache 2.0 |
Mistral's voice in 8B, Apache 2.0. | Q5_K_M · 7.6 GB | 35 | Runs great |
| Best vision | Qwen3.5 9B Alibaba · Apache 2.0 |
Vision on an 8–12 GB card. | Q5_K_M · 7.2 GB | 32 | Runs great |
| Best for agents | Granite 4.1 8B IBM · Apache 2.0 |
Enterprise-grade tool calling in a dense 8B, no thinking overhead. | Q5_K_M · 7.7 GB | 35 | Runs great |
| Best translation | Qwen3.5 9B Alibaba · Apache 2.0 |
Strong CJK and European translation in 8–12 GB. | Q5_K_M · 7.2 GB | 32 | Runs great |
| Fastest good model | LFM2.5 8B-A1B Liquid AI · LFM Open License v1.0 |
1.5B active; designed for laptops without a GPU. | Q5_K_M · 6.3 GB | 79 | Runs great |
| Best long context | Qwen3.5 4B Alibaba · Apache 2.0 |
262K on 8 GB. | Q5_K_M · 7.7 GB at 128K context |
66 | Runs great |
Everything that fits
Runs great
29 of 80 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 8K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5 9B | 9.65B | Q5_K_M | 6.4 GB | 0.25 GB | 7.2 GB |
3.4 GB free
|
32 | Ollama | Run |
| Ornith 1.5 9B | 9.41B | Q5_K_M | 6.2 GB | 0.25 GB | 7.1 GB |
3.5 GB free
|
33 | Ollama | Run |
| Ministral 3 8B | 8.92B | Q5_K_M | 5.9 GB | 1.06 GB | 7.6 GB |
3.0 GB free
|
35 | Ollama | Run |
| Granite 4.1 8B | 8.79B | Q5_K_M | 5.8 GB | 1.25 GB | 7.7 GB |
2.9 GB free
|
35 | Ollama | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q5_K_M | 5.6 GB | 0.09 GB | 6.3 GB |
4.3 GB free
|
79 | Ollama | Run |
| Fara 7B | 8.29B | Q5_K_M | 5.5 GB | 0.44 GB | 6.5 GB |
4.1 GB free
|
37 | llama.cpp | Run |
| Qwen3 8B | 8.19B | Q5_K_M | 5.4 GB | 1.13 GB | 7.1 GB |
3.5 GB free
|
38 | Ollama | Run |
| Llama 3.1 8B Instruct | 8.03B | Q5_K_M | 5.3 GB | 1.00 GB | 6.9 GB |
3.7 GB free
|
38 | Ollama | Run |
| Gemma 4 E4B | 8.0B | Q5_K_M | 5.3 GB | 0.14 GB | 6.0 GB |
4.6 GB free
|
39 | Ollama | Run |
| Ling 3.0 Tiny 7.9B-A1.3B | 7.9B MoE / 1.3B act | Q5_K_M | 5.2 GB | 0.05 GB | 5.9 GB |
4.7 GB free
|
91 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q5_K_M | 5.0 GB | 0.44 GB | 6.1 GB |
4.5 GB free
|
40 | Ollama | Run |
| Qwen2.5-Coder 7B | 7.62B | Q5_K_M | 5.0 GB | 0.44 GB | 6.1 GB |
4.5 GB free
|
40 | Ollama | Run |
| Olmo 3 7B Instruct | 7.3B | Q5_K_M | 4.8 GB | 2.50 GB | 7.9 GB |
2.7 GB free
|
42 | Ollama | Run |
| Mistral 7B Instruct v0.3 | 7.25B | Q5_K_M | 4.8 GB | 1.00 GB | 6.4 GB |
4.2 GB free
|
43 | Ollama | Run |
| Gemma 4 E2B | 5.1B | Q5_K_M | 3.4 GB | 0.07 GB | 4.0 GB |
6.6 GB free
|
60 | Ollama | Run |
| Qwen3.5 4B | 4.66B | Q5_K_M | 3.1 GB | 0.25 GB | 3.9 GB |
6.7 GB free
|
66 | Ollama | Run |
| Gemma 3 4B | 4.3B | Q5_K_M | 2.8 GB | 0.30 GB | 3.7 GB |
6.9 GB free
|
72 | Ollama | Run |
| Qwen3 4B | 4.02B | Q5_K_M | 2.7 GB | 1.13 GB | 4.4 GB |
6.2 GB free
|
77 | Ollama | Run |
| Ministral 3 3B | 3.85B | Q5_K_M | 2.5 GB | 0.81 GB | 4.0 GB |
6.6 GB free
|
80 | Ollama | Run |
| Phi-4-mini 3.8B | 3.84B | Q5_K_M | 2.5 GB | 1.00 GB | 4.1 GB |
6.5 GB free
|
80 | Ollama | Run |
| Granite 4.1 3B | 3.4B | Q5_K_M | 2.2 GB | 0.63 GB | 3.5 GB |
7.1 GB free
|
91 | Ollama | Run |
| Llama 3.2 3B Instruct | 3.21B | Q5_K_M | 2.1 GB | 0.88 GB | 3.6 GB |
7.0 GB free
|
96 | Ollama | Run |
| LFM2.5 2.6B | 2.7B | Q5_K_M | 1.8 GB | 0.13 GB | 2.5 GB |
8.1 GB free
|
114 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q5_K_M | 1.5 GB | 0.09 GB | 2.2 GB |
8.4 GB free
|
136 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q5_K_M | 1.1 GB | 0.88 GB | 2.6 GB |
8.0 GB free
|
179 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q5_K_M | 0.8 GB | 0.25 GB | 1.7 GB |
8.9 GB free
|
249 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q5_K_M | 0.7 GB | 0.04 GB | 1.3 GB |
9.3 GB free
|
308 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q5_K_M | 0.6 GB | 0.09 GB | 1.3 GB |
9.3 GB free
|
354 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q5_K_M | 0.4 GB | 0.88 GB | 1.9 GB |
8.7 GB free
|
514 | Ollama | Run |
Runs — tight
3 models · fits at 8K, drop context or quant to go longer| Model | Params | Quant | Weights | +KV 8K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 3 12B | 12.2B | Q5_K_M | 8.1 GB | 0.81 GB | 9.5 GB |
1.1 GB free
|
25 | llama.cpp | Run |
| Mistral NeMo 12B | 12.2B | Q5_K_M | 8.1 GB | 1.25 GB | 9.9 GB |
0.7 GB free
|
25 | llama.cpp | Run |
| Gemma 4 12B | 12B | Q5_K_M | 7.9 GB | 0.81 GB | 9.3 GB |
1.3 GB free
|
26 | llama.cpp | Run |
Won't fit in VRAM
48 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 8K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5.3-Flash 320B-A18B | 321B MoE / 18B act | Q5_K_M | 211.9 GB | 0.09 GB | 212.6 GB | +202.0 GB | ~1.2 | llama.cpp | Why |
| DeepSeek V4 Flash 284B-A13B | 284B MoE / 13B act | Q5_K_M | 187.5 GB | 0.38 GB | 188.4 GB | +177.8 GB | ~1.7 | llama.cpp | Why |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q5_K_M | 155.1 GB | 1.47 GB | 157.2 GB | +146.6 GB | ~1.0 | llama.cpp | Why |
| Qwen3.8-Flash-Next 180B-A6B | 180B MoE / 6B act | Q5_K_M | 118.8 GB | 0.19 GB | 119.6 GB | +109.0 GB | ~3.8 | llama.cpp | Why |
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q5_K_M | 82.5 GB | 0.19 GB | 83.3 GB | +72.7 GB | ~2.3 | llama.cpp | Why |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q5_K_M | 81.8 GB | 0.06 GB | 82.5 GB | +71.9 GB | ~2.0 | llama.cpp | Why |
| Ling 3.0 Flash 124B-A5B | 124B MoE / 5.1B act | Q5_K_M | 81.8 GB | 0.06 GB | 82.5 GB | +71.9 GB | ~4.6 | llama.cpp | Why |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q5_K_M | 78.5 GB | 0.18 GB | 79.3 GB | +68.7 GB | ~3.6 | llama.cpp | Why |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 0.29 GB | 61.4 GB | +50.8 GB | ~6.1 | llama.cpp | Why |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q5_K_M | 71.9 GB | 1.50 GB | 74.0 GB | +63.4 GB | ~1.4 | llama.cpp | Why |
| Llama 3.3 70B Instruct | 70.6B | Q5_K_M | 46.6 GB | 2.50 GB | 49.7 GB | +39.1 GB | ~0.9 | llama.cpp | Why |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q5_K_M | 46.6 GB | 2.50 GB | 49.7 GB | +39.1 GB | ~0.9 | llama.cpp | Why |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q5_K_M | 23.7 GB | 0.16 GB | 24.5 GB | +13.9 GB | ~9.7 | llama.cpp | Why |
| Ornith 1.5 35B-A3B | 35.9B MoE / 3.3B act | Q5_K_M | 23.7 GB | 0.16 GB | 24.5 GB | +13.9 GB | ~9.7 | llama.cpp | Why |
| LLM-jp 4 33B Thinking | 33.2B | Q5_K_M | 21.9 GB | 2.00 GB | 24.5 GB | +13.9 GB | ~2.4 | llama.cpp | Why |
| Qwen3 32B | 32.8B | Q5_K_M | 21.7 GB | 2.00 GB | 24.3 GB | +13.7 GB | ~2.4 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q5_K_M | 21.7 GB | 2.00 GB | 24.3 GB | +13.7 GB | ~2.4 | llama.cpp | Why |
| Qwen2.5-Coder 32B | 32.8B | Q5_K_M | 21.7 GB | 2.00 GB | 24.3 GB | +13.7 GB | ~2.4 | llama.cpp | Why |
| Olmo 3.1 32B Instruct | 32.2B | Q5_K_M | 21.3 GB | 1.25 GB | 23.1 GB | +12.5 GB | ~2.6 | llama.cpp | Why |
| Nemotron 3.5 Lightning 30B-A3B | 31.6B MoE / 3.2B act | Q5_K_M | 20.9 GB | 0.05 GB | 21.5 GB | +10.9 GB | ~11 | llama.cpp | Why |
| Gemma 4 31B | 31.3B | Q5_K_M | 20.7 GB | 2.03 GB | 23.3 GB | +12.7 GB | ~2.6 | llama.cpp | Why |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q5_K_M | 20.6 GB | 0.41 GB | 21.6 GB | +11.0 GB | ~11 | llama.cpp | Why |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q5_K_M | 20.1 GB | 0.75 GB | 21.5 GB | +10.9 GB | ~10 | llama.cpp | Why |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q5_K_M | 20.1 GB | 0.75 GB | 21.5 GB | +10.9 GB | ~10 | llama.cpp | Why |
| Muse Glimmer 30B | 29.8B | Q5_K_M | 19.7 GB | 0.18 GB | 20.4 GB | +9.8 GB | ~3.1 | llama.cpp | Why |
| Granite 4.1 30B | 28.9B | Q5_K_M | 19.1 GB | 2.00 GB | 21.7 GB | +11.1 GB | ~2.9 | llama.cpp | Why |
| Qwen3.8 27B | 27.8B | Q5_K_M | 18.4 GB | 0.50 GB | 19.5 GB | +8.9 GB | ~3.4 | llama.cpp | Why |
| Qwen3.6 27B | 27.8B | Q5_K_M | 18.4 GB | 0.50 GB | 19.5 GB | +8.9 GB | ~3.4 | llama.cpp | Why |
| Gemma 3 27B | 27.4B | Q5_K_M | 18.1 GB | 1.03 GB | 19.7 GB | +9.1 GB | ~3.4 | llama.cpp | Why |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q5_K_M | 17.5 GB | 0.51 GB | 18.6 GB | +8.0 GB | ~10 | llama.cpp | Why |
| Devstral Small 2 24B | 24B | Q5_K_M | 15.8 GB | 1.25 GB | 17.7 GB | +7.1 GB | ~4.2 | llama.cpp | Why |
| Mistral Small 3.2 24B | 23.6B | Q5_K_M | 15.6 GB | 1.25 GB | 17.4 GB | +6.8 GB | ~4.3 | llama.cpp | Why |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 0.19 GB | 11.6 GB | +1.0 GB | ~29 | llama.cpp | Why |
| Qwen3 14B | 14.8B | Q5_K_M | 9.8 GB | 1.25 GB | 11.6 GB | +1.0 GB | ~14 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q5_K_M | 9.8 GB | 1.50 GB | 11.9 GB | +1.3 GB | ~13 | llama.cpp | Why |
| Qwen2.5-Coder 14B | 14.8B | Q5_K_M | 9.8 GB | 1.50 GB | 11.9 GB | +1.3 GB | ~13 | llama.cpp | Why |
| Phi-4 14B | 14.7B | Q5_K_M | 9.7 GB | 1.56 GB | 11.9 GB | +1.3 GB | ~13 | llama.cpp | Why |
| Ministral 3 14B | 13.9B | Q5_K_M | 9.2 GB | 1.25 GB | 11.0 GB | +0.4 GB | ~18 | llama.cpp | Why |
| Kimi K3 2.8T-A104B | 2780B MoE / 104B act | Q5_K_M | 1835.0 GB | 0.21 GB | 1835.8 GB | +1825.2 GB | ~0.2 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B | 2446B MoE / 95B act | Q5_K_M | 1614.5 GB | 0.72 GB | 1615.9 GB | +1605.3 GB | ~0.2 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B | 1650B MoE / 49B act | Q5_K_M | 1089.1 GB | 0.54 GB | 1090.3 GB | +1079.7 GB | ~0.4 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q5_K_M | 677.9 GB | 0.54 GB | 679.0 GB | +668.4 GB | ~0.7 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q5_K_M | 497.0 GB | 0.69 GB | 498.3 GB | +487.7 GB | ~0.5 | llama.cpp | Why |
| GLM-5.3 744B-A40B | 753B MoE / 40B act | Q5_K_M | 497.0 GB | 0.69 GB | 498.3 GB | +487.7 GB | ~0.5 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q5_K_M | 442.9 GB | 0.54 GB | 444.0 GB | +433.4 GB | ~0.6 | llama.cpp | Why |
| DeepSeek V4.1 Flash 552B-A16B New | 552B MoE / 16B act | Q5_K_M | 364.4 GB | 0.04 GB | 365.0 GB | +354.4 GB | ~1.4 | vLLM | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q5_K_M | 266.0 GB | 0.23 GB | 266.8 GB | +256.2 GB | ~1.3 | llama.cpp | Why |
| Ornith 1.5 397B-A17B | 397B MoE / 17B act | Q5_K_M | 262.0 GB | 0.23 GB | 262.9 GB | +252.3 GB | ~1.3 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 8K tokens + 0.6 GB runtime overhead, against 10.6 GB usable VRAM (12 GB less display and driver reserve). Tokens per second are estimated from 336 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.
Same memory, different speed
10 of the 12 devices have the same 10.6 GB usable, so they run exactly the models above. Generation speed scales with memory bandwidth.
| Device | Bandwidth | Speed vs yours |
|---|---|---|
| GeForce RTX 3080 Ti Ampere · 2021 |
912 GB/s | 2.71× |
| GeForce RTX 3080 12 GB Ampere · 2022 |
912 GB/s | 2.71× |
| GeForce RTX 5070 Blackwell · 2025 |
672 GB/s | 2.00× |
| GeForce RTX 4070 Ti Ada Lovelace · 2023 |
504 GB/s | 1.50× |
| GeForce RTX 4070 Super Ada Lovelace · 2024 |
504 GB/s | 1.50× |
| GeForce RTX 4070 Ada Lovelace · 2023 |
504 GB/s | 1.50× |
| Arc B580 Battlemage · 2024 |
456 GB/s | 1.36× |
| GeForce RTX 4080 Laptop Ada Lovelace · 2023 |
432 GB/s | 1.29× |
| Radeon RX 7700 XT RDNA 3 · 2023 |
432 GB/s | 1.29× |
| GeForce RTX 3060 12 GB Ampere · 2021 |
360 GB/s | 1.07× |
What more memory unlocks
At Q4_K_M and 8K context this device fits 37 of 80 models. Each step up, and the largest models it adds:
| Step up | Models fit | Adds, largest first |
|---|---|---|
| 16 GB card e.g. GeForce RTX 5080 |
38 (+1) | gpt-oss 20B |
| 24 GB card e.g. GeForce RTX 4090 |
58 (+21) | Qwen3.6 35B-A3B, Ornith 1.5 35B-A3B, LLM-jp 4 33B Thinking |
| 32 GB card e.g. GeForce RTX 5090 |
58 (+21) | Qwen3.6 35B-A3B, Ornith 1.5 35B-A3B, LLM-jp 4 33B Thinking |