Your rig
Radeon RX 6600 · 8 GB
Which one should I actually run?
Best models for your Radeon RX 6600
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 32K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.
| Recommendation | Model | Why | Quant · total | Tok/s est. | |
|---|---|---|---|---|---|
| Best overall | Gemma 4 E4B Google · Apache 2.0 |
Laptop class with images and audio in. | Q3_K_M · 4.7 GB | 37 | Runs great |
| Best for coding | Ornith 1.5 9B Ornith AI · MIT |
A coding-agent reasoning build on the Qwen3.5 9B architecture. | Q3_K_M · 5.9 GB | 32 | Runs great |
| Best reasoning | Qwen3.5 4B Alibaba · Apache 2.0 |
Step-by-step reasoning in 8 GB. | Q3_K_M · 3.7 GB | 64 | Runs great |
| Best for writing | Gemma 4 E4B Google · Apache 2.0 |
Readable prose on a laptop. | Q3_K_M · 4.7 GB | 37 | Runs great |
| Best vision | Gemma 4 E4B Google · Apache 2.0 |
Laptop vision, audio too. | Q3_K_M · 4.7 GB | 37 | Runs great |
| Best for agents | Qwen3.5 4B Alibaba · Apache 2.0 |
Function calling in 8 GB. | Q3_K_M · 3.7 GB | 64 | Runs great |
| Best translation | Gemma 4 E4B Google · Apache 2.0 |
140+ languages on a laptop. | Q3_K_M · 4.7 GB | 37 | 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. | Q3_K_M · 4.8 GB | 76 | Runs great |
| Best long context | Qwen3.5 2B Alibaba · Apache 2.0 |
Long documents on 4 GB. | Q3_K_M · 3.1 GB at 128K context |
131 | Runs great |
Everything that fits
Runs great
19 of 80 · fits with headroom for a longer prompt| Model | Params | Quant | Weights | +KV 32K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Ornith 1.5 9B | 9.41B | Q3_K_M | 4.3 GB | 1.00 GB | 5.9 GB |
1.1 GB free
|
32 | Ollama | Run |
| LFM2.5 8B-A1B | 8.47B MoE / 1.5B act | Q3_K_M | 3.9 GB | 0.38 GB | 4.8 GB |
2.2 GB free
|
76 | Ollama | Run |
| Gemma 4 E4B | 8.0B | Q3_K_M | 3.6 GB | 0.47 GB | 4.7 GB |
2.3 GB free
|
37 | Ollama | Run |
| Ling 3.0 Tiny 7.9B-A1.3B | 7.9B MoE / 1.3B act | Q3_K_M | 3.6 GB | 0.21 GB | 4.4 GB |
2.6 GB free
|
88 | llama.cpp | Run |
| DeepSeek-R1-Distill-Qwen 7B | 7.62B | Q3_K_M | 3.5 GB | 1.75 GB | 5.8 GB |
1.2 GB free
|
39 | Ollama | Run |
| Qwen2.5-Coder 7B | 7.62B | Q3_K_M | 3.5 GB | 1.75 GB | 5.8 GB |
1.2 GB free
|
39 | Ollama | Run |
| Gemma 4 E2B | 5.1B | Q3_K_M | 2.3 GB | 0.23 GB | 3.2 GB |
3.8 GB free
|
58 | Ollama | Run |
| Qwen3.5 4B | 4.66B | Q3_K_M | 2.1 GB | 1.00 GB | 3.7 GB |
3.3 GB free
|
64 | Ollama | Run |
| Gemma 3 4B | 4.3B | Q3_K_M | 2.0 GB | 0.86 GB | 3.4 GB |
3.6 GB free
|
69 | Ollama | Run |
| Ministral 3 3B | 3.85B | Q3_K_M | 1.8 GB | 3.25 GB | 5.6 GB |
1.4 GB free
|
77 | Ollama | Run |
| Granite 4.1 3B | 3.4B | Q3_K_M | 1.5 GB | 2.50 GB | 4.6 GB |
2.4 GB free
|
88 | Ollama | Run |
| Llama 3.2 3B Instruct | 3.21B | Q3_K_M | 1.5 GB | 3.50 GB | 5.6 GB |
1.4 GB free
|
93 | Ollama | Run |
| LFM2.5 2.6B | 2.7B | Q3_K_M | 1.2 GB | 0.50 GB | 2.3 GB |
4.7 GB free
|
110 | llama.cpp | Run |
| Qwen3.5 2B | 2.27B | Q3_K_M | 1.0 GB | 0.38 GB | 2.0 GB |
5.0 GB free
|
131 | Ollama | Run |
| Qwen3 1.7B | 1.72B | Q3_K_M | 0.8 GB | 3.50 GB | 4.9 GB |
2.1 GB free
|
173 | Ollama | Run |
| Llama 3.2 1B Instruct | 1.24B | Q3_K_M | 0.6 GB | 1.00 GB | 2.2 GB |
4.8 GB free
|
240 | Ollama | Run |
| Gemma 3 1B | 1.0B | Q3_K_M | 0.5 GB | 0.14 GB | 1.2 GB |
5.8 GB free
|
298 | Ollama | Run |
| Qwen3.5 0.8B | 0.87B | Q3_K_M | 0.4 GB | 0.38 GB | 1.4 GB |
5.6 GB free
|
342 | Ollama | Run |
| Qwen3 0.6B | 0.6B | Q3_K_M | 0.3 GB | 3.50 GB | 4.4 GB |
2.6 GB free
|
497 | Ollama | Run |
Runs — tight
4 models · fits at 32K, drop context or quant to go longer| Model | Params | Quant | Weights | +KV 32K | Total | VRAM headroom | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5 9B | 9.65B | Q3_K_M | 4.4 GB | 1.00 GB | 6.0 GB |
1.0 GB free
|
31 | llama.cpp | Run |
| Fara 7B | 8.29B | Q3_K_M | 3.8 GB | 1.75 GB | 6.1 GB |
0.9 GB free
|
36 | llama.cpp | Run |
| Qwen3 4B | 4.02B | Q3_K_M | 1.8 GB | 4.50 GB | 6.9 GB |
0.1 GB free
|
74 | llama.cpp | Run |
| Phi-4-mini 3.8B | 3.84B | Q3_K_M | 1.7 GB | 4.00 GB | 6.3 GB |
0.7 GB free
|
78 | llama.cpp | Run |
Won't fit in VRAM
57 models · some are possible with CPU offload| Model | Params | Quant | Weights | +KV 32K | Total | Over budget | Tok/s | Runtime | |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5 122B-A10B | 125B MoE / 10B act | Q3_K_M | 56.9 GB | 0.75 GB | 58.2 GB | +51.2 GB | ~3.3 | llama.cpp | Why |
| Nemotron 3 Super 120B-A12B | 124B MoE / 12B act | Q3_K_M | 56.4 GB | 0.25 GB | 57.3 GB | +50.3 GB | ~2.8 | llama.cpp | Why |
| Ling 3.0 Flash 124B-A5B | 124B MoE / 5.1B act | Q3_K_M | 56.4 GB | 0.25 GB | 57.3 GB | +50.3 GB | ~6.5 | llama.cpp | Why |
| Mistral Small 4 119B-A6B | 119B MoE / 6.5B act | Q3_K_M | 54.2 GB | 0.70 GB | 55.5 GB | +48.5 GB | ~5.1 | llama.cpp | Why |
| Llama 4 Scout 109B-A17B | 109B MoE / 17B act | Q3_K_M | 49.6 GB | 2.63 GB | 52.8 GB | +45.8 GB | ~1.9 | llama.cpp | Why |
| Llama 3.3 70B Instruct | 70.6B | Q3_K_M | 32.1 GB | 10.00 GB | 42.7 GB | +35.7 GB | ~1.1 | llama.cpp | Why |
| DeepSeek-R1-Distill-Llama 70B | 70.6B | Q3_K_M | 32.1 GB | 10.00 GB | 42.7 GB | +35.7 GB | ~1.1 | llama.cpp | Why |
| Qwen3.6 35B-A3B | 35.9B MoE / 3.3B act | Q3_K_M | 16.3 GB | 0.63 GB | 17.6 GB | +10.6 GB | ~13 | llama.cpp | Why |
| Ornith 1.5 35B-A3B | 35.9B MoE / 3.3B act | Q3_K_M | 16.3 GB | 0.63 GB | 17.6 GB | +10.6 GB | ~13 | llama.cpp | Why |
| LLM-jp 4 33B Thinking | 33.2B | Q3_K_M | 15.1 GB | 8.00 GB | 23.7 GB | +16.7 GB | ~2.4 | llama.cpp | Why |
| Qwen3 32B | 32.8B | Q3_K_M | 14.9 GB | 8.00 GB | 23.5 GB | +16.5 GB | ~2.4 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | Q3_K_M | 14.9 GB | 8.00 GB | 23.5 GB | +16.5 GB | ~2.4 | llama.cpp | Why |
| Qwen2.5-Coder 32B | 32.8B | Q3_K_M | 14.9 GB | 8.00 GB | 23.5 GB | +16.5 GB | ~2.4 | llama.cpp | Why |
| Olmo 3.1 32B Instruct | 32.2B | Q3_K_M | 14.7 GB | 2.75 GB | 18.0 GB | +11.0 GB | ~3.0 | llama.cpp | Why |
| Nemotron 3.5 Lightning 30B-A3B | 31.6B MoE / 3.2B act | Q3_K_M | 14.4 GB | 0.19 GB | 15.2 GB | +8.2 GB | ~14 | llama.cpp | Why |
| Gemma 4 31B | 31.3B | Q3_K_M | 14.2 GB | 5.78 GB | 20.6 GB | +13.6 GB | ~2.6 | llama.cpp | Why |
| GLM-4.7-Flash 30B-A3B | 31.2B MoE / 3B act | Q3_K_M | 14.2 GB | 1.65 GB | 16.5 GB | +9.5 GB | ~14 | llama.cpp | Why |
| Qwen3 30B-A3B | 30.5B MoE / 3.3B act | Q3_K_M | 13.9 GB | 3.00 GB | 17.5 GB | +10.5 GB | ~11 | llama.cpp | Why |
| Qwen3 Coder 30B-A3B | 30.5B MoE / 3.3B act | Q3_K_M | 13.9 GB | 3.00 GB | 17.5 GB | +10.5 GB | ~11 | llama.cpp | Why |
| Muse Glimmer 30B | 29.8B | Q3_K_M | 13.6 GB | 0.48 GB | 14.6 GB | +7.6 GB | ~3.9 | llama.cpp | Why |
| Granite 4.1 30B | 28.9B | Q3_K_M | 13.2 GB | 8.00 GB | 21.8 GB | +14.8 GB | ~2.8 | llama.cpp | Why |
| Qwen3.8 27B | 27.8B | Q3_K_M | 12.7 GB | 2.00 GB | 15.3 GB | +8.3 GB | ~3.9 | llama.cpp | Why |
| Qwen3.6 27B | 27.8B | Q3_K_M | 12.7 GB | 2.00 GB | 15.3 GB | +8.3 GB | ~3.9 | llama.cpp | Why |
| Gemma 3 27B | 27.4B | Q3_K_M | 12.5 GB | 2.91 GB | 16.0 GB | +9.0 GB | ~3.7 | llama.cpp | Why |
| Gemma 4 26B-A4B | 26.5B MoE / 3.8B act | Q3_K_M | 12.1 GB | 1.45 GB | 14.1 GB | +7.1 GB | ~12 | llama.cpp | Why |
| Devstral Small 2 24B | 24B | Q3_K_M | 10.9 GB | 5.00 GB | 16.5 GB | +9.5 GB | ~3.7 | llama.cpp | Why |
| Mistral Small 3.2 24B | 23.6B | Q3_K_M | 10.7 GB | 5.00 GB | 16.3 GB | +9.3 GB | ~3.7 | llama.cpp | Why |
| gpt-oss 20B | 20.9B MoE / 3.6B act | MXFP4 | 10.8 GB | 0.75 GB | 12.2 GB | +5.2 GB | ~12 | llama.cpp | Why |
| Qwen3 14B | 14.8B | Q3_K_M | 6.7 GB | 5.00 GB | 12.3 GB | +5.3 GB | ~6.4 | llama.cpp | Why |
| DeepSeek-R1-Distill-Qwen 14B | 14.8B | Q3_K_M | 6.7 GB | 6.00 GB | 13.3 GB | +6.3 GB | ~5.6 | llama.cpp | Why |
| Qwen2.5-Coder 14B | 14.8B | Q3_K_M | 6.7 GB | 6.00 GB | 13.3 GB | +6.3 GB | ~5.6 | llama.cpp | Why |
| Phi-4 14B | 14.7B | Q3_K_M | 6.7 GB | 3.13 GB | 10.4 GB | +3.4 GB | ~8.5 | llama.cpp | Why |
| Ministral 3 14B | 13.9B | Q3_K_M | 6.3 GB | 5.00 GB | 11.9 GB | +4.9 GB | ~6.9 | llama.cpp | Why |
| Gemma 3 12B | 12.2B | Q3_K_M | 5.6 GB | 2.31 GB | 8.5 GB | +1.5 GB | ~14 | llama.cpp | Why |
| Mistral NeMo 12B | 12.2B | Q3_K_M | 5.6 GB | 5.00 GB | 11.2 GB | +4.2 GB | ~8.0 | llama.cpp | Why |
| Gemma 4 12B | 12B | Q3_K_M | 5.5 GB | 2.31 GB | 8.4 GB | +1.4 GB | ~15 | llama.cpp | Why |
| Ministral 3 8B | 8.92B | Q3_K_M | 4.1 GB | 4.25 GB | 8.9 GB | +1.9 GB | ~15 | llama.cpp | Why |
| Granite 4.1 8B | 8.79B | Q3_K_M | 4.0 GB | 5.00 GB | 9.6 GB | +2.6 GB | ~12 | llama.cpp | Why |
| Qwen3 8B | 8.19B | Q3_K_M | 3.7 GB | 4.50 GB | 8.8 GB | +1.8 GB | ~16 | llama.cpp | Why |
| Llama 3.1 8B Instruct | 8.03B | Q3_K_M | 3.7 GB | 4.00 GB | 8.3 GB | +1.3 GB | ~19 | llama.cpp | Why |
| Olmo 3 7B Instruct | 7.3B | Q3_K_M | 3.3 GB | 5.50 GB | 9.4 GB | +2.4 GB | ~14 | llama.cpp | Why |
| Mistral 7B Instruct v0.3 | 7.25B | Q3_K_M | 3.3 GB | 4.00 GB | 7.9 GB | +0.9 GB | ~24 | llama.cpp | Why |
| Kimi K3 2.8T-A104B | 2780B MoE / 104B act | Q3_K_M | 1265.4 GB | 0.84 GB | 1266.9 GB | +1259.9 GB | ~0.3 | llama.cpp | Why |
| Qwen3.8 2.4T-A95B | 2446B MoE / 95B act | Q3_K_M | 1113.4 GB | 2.88 GB | 1116.9 GB | +1109.9 GB | ~0.3 | llama.cpp | Why |
| DeepSeek V4 Pro 1.6T-A49B | 1650B MoE / 49B act | Q3_K_M | 751.1 GB | 2.14 GB | 753.8 GB | +746.8 GB | ~0.6 | llama.cpp | Why |
| Kimi K2.6 1T-A32B | 1027B MoE / 32B act | Q3_K_M | 467.5 GB | 2.14 GB | 470.2 GB | +463.2 GB | ~1.0 | llama.cpp | Why |
| GLM-5.2 744B-A40B | 753B MoE / 40B act | Q3_K_M | 342.8 GB | 2.74 GB | 346.1 GB | +339.1 GB | ~0.8 | llama.cpp | Why |
| GLM-5.3 744B-A40B | 753B MoE / 40B act | Q3_K_M | 342.8 GB | 2.74 GB | 346.1 GB | +339.1 GB | ~0.8 | llama.cpp | Why |
| DeepSeek-R1 671B | 671B MoE / 37B act | Q3_K_M | 305.4 GB | 2.14 GB | 308.2 GB | +301.2 GB | ~0.8 | llama.cpp | Why |
| DeepSeek V4.1 Flash 552B-A16B New | 552B MoE / 16B act | Q3_K_M | 251.3 GB | 0.15 GB | 252.0 GB | +245.0 GB | ~2.0 | — | Why |
| Qwen3.5 397B-A17B | 403B MoE / 17B act | Q3_K_M | 183.4 GB | 0.94 GB | 185.0 GB | +178.0 GB | ~1.8 | llama.cpp | Why |
| Ornith 1.5 397B-A17B | 397B MoE / 17B act | Q3_K_M | 180.7 GB | 0.94 GB | 182.2 GB | +175.2 GB | ~1.8 | llama.cpp | Why |
| GLM-5.3-Flash 320B-A18B | 321B MoE / 18B act | Q3_K_M | 146.1 GB | 0.34 GB | 147.1 GB | +140.1 GB | ~1.8 | llama.cpp | Why |
| DeepSeek V4 Flash 284B-A13B | 284B MoE / 13B act | Q3_K_M | 129.3 GB | 1.51 GB | 131.4 GB | +124.4 GB | ~2.4 | llama.cpp | Why |
| Qwen3 235B-A22B | 235B MoE / 22B act | Q3_K_M | 107.0 GB | 5.88 GB | 113.4 GB | +106.4 GB | ~1.4 | llama.cpp | Why |
| Qwen3.8-Flash-Next 180B-A6B | 180B MoE / 6B act | Q3_K_M | 81.9 GB | 0.75 GB | 83.3 GB | +76.3 GB | ~5.4 | llama.cpp | Why |
| gpt-oss 120B | 117B MoE / 5.1B act | MXFP4 | 60.5 GB | 1.13 GB | 62.2 GB | +55.2 GB | ~5.6 | llama.cpp | Why |
Totals = quantised weights + f16 KV cache at 32K 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 224 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 7.0 GB usable, so they run exactly the models above. Generation speed scales with memory bandwidth.
| Device | Bandwidth | Speed vs yours |
|---|---|---|
| GeForce RTX 3070 Ti Ampere · 2021 |
608 GB/s | 2.71× |
| Arc A750 Alchemist · 2022 |
512 GB/s | 2.29× |
| GeForce RTX 2080 Super Turing · 2019 |
496 GB/s | 2.21× |
| GeForce RTX 5060 Blackwell · 2025 |
448 GB/s | 2.00× |
| GeForce RTX 3070 Ampere · 2020 |
448 GB/s | 2.00× |
| GeForce RTX 3060 Ti Ampere · 2020 |
448 GB/s | 2.00× |
| GeForce RTX 4060 Ti Ada Lovelace · 2023 |
288 GB/s | 1.29× |
| GeForce RTX 4060 Ada Lovelace · 2023 |
272 GB/s | 1.21× |
| GeForce RTX 4070 Laptop Ada Lovelace · 2023 |
256 GB/s | 1.14× |
| GeForce RTX 4060 Laptop Ada Lovelace · 2023 |
256 GB/s | 1.14× |
What more memory unlocks
At Q4_K_M and 8K context this device fits 28 of 80 models. Each step up, and the largest models it adds:
| Step up | Models fit | Adds, largest first |
|---|---|---|
| 12 GB card | 37 (+9) | Qwen3 14B, DeepSeek-R1-Distill-Qwen 14B, Qwen2.5-Coder 14B |
| 16 GB card e.g. GeForce RTX 5080 |
38 (+10) | gpt-oss 20B, Qwen3 14B, DeepSeek-R1-Distill-Qwen 14B |
| 24 GB card e.g. GeForce RTX 4090 |
58 (+30) | Qwen3.6 35B-A3B, Ornith 1.5 35B-A3B, LLM-jp 4 33B Thinking |