What LLMs can a Radeon RX 6700 XT run?

Your rig

Radeon RX 6700 XT · 12 GB

8 GB system RAM · RDNA 2 · 384 GB/s · 10.6 GB usable VRAM

Which one should I actually run?

Best models for your Radeon RX 6700 XT

Updated 21 Aug 2026 5 new this week, 14 this month

What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q6_K and 32K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.

All General assistant Coding Reasoning & maths Writing Vision Agents & tool use Translation Low latency Long context

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.	Q6_K · 9.0 GB	32	Runs great Run
Best for coding	Qwen3.5 9B Alibaba · Apache 2.0	The best coding model for 8–12 GB cards.	Q6_K · 9.0 GB	32	Runs great Run
Best reasoning	Qwen3.5 9B Alibaba · Apache 2.0	Thinking mode on a 12 GB card — ahead of the 2025 R1 distills.	Q6_K · 9.0 GB	32	Runs great Run
Best for writing	Gemma 4 E4B Google · Apache 2.0	Readable prose on a laptop.	Q6_K · 7.2 GB	38	Runs great Run
Best vision	Qwen3.5 9B Alibaba · Apache 2.0	Vision on an 8–12 GB card.	Q6_K · 9.0 GB	32	Runs great Run
Best for agents	Fara 7B Microsoft · MIT	Web computer-use only — clicks and fills forms from screenshots, and stops to ask before anything irreversible.	Q6_K · 8.7 GB	37	Runs great Run
Best translation	Qwen3.5 9B Alibaba · Apache 2.0	Strong CJK and European translation in 8–12 GB.	Q6_K · 9.0 GB	32	Runs great Run
Fastest good model	LFM2.5 8B-A1B Liquid AI · LFM Open License v1.0	1.5B active; designed for laptops without a GPU.	Q6_K · 7.4 GB	78	Runs great Run
Best long context	Qwen3.5 4B Alibaba · Apache 2.0	262K on 8 GB.	Q6_K · 8.2 GB at 128K context	65	Runs great Run

Everything that fits

Runs great

23 of 76 · fits with headroom for a longer prompt

Model	Params	Quant	Weights	+KV 32K	Total	VRAM headroom	Tok/s	Runtime
Qwen3.5 9B	9.65B	Q6_K	7.4 GB	1.00 GB	9.0 GB	1.6 GB free	32	Ollama	Run
Ornith 1.5 9B New this week	9.41B	Q6_K	7.2 GB	1.00 GB	8.8 GB	1.8 GB free	32	Ollama	Run
LFM2.5 8B-A1B	8.47B MoE / 1.5B act	Q6_K	6.5 GB	0.38 GB	7.4 GB	3.2 GB free	78	Ollama	Run
Fara 7B	8.29B	Q6_K	6.3 GB	1.75 GB	8.7 GB	1.9 GB free	37	llama.cpp	Run
Gemma 4 E4B	8.0B	Q6_K	6.1 GB	0.47 GB	7.2 GB	3.4 GB free	38	Ollama	Run
Ling 3.0 Tiny 7.9B-A1.3B New	7.9B MoE / 1.3B act	Q6_K	6.0 GB	0.21 GB	6.8 GB	3.8 GB free	90	llama.cpp	Run
DeepSeek-R1-Distill-Qwen 7B	7.62B	Q6_K	5.8 GB	1.75 GB	8.2 GB	2.4 GB free	40	Ollama	Run
Qwen2.5-Coder 7B	7.62B	Q6_K	5.8 GB	1.75 GB	8.2 GB	2.4 GB free	40	Ollama	Run
Gemma 4 E2B	5.1B	Q6_K	3.9 GB	0.23 GB	4.7 GB	5.9 GB free	60	Ollama	Run
Qwen3.5 4B	4.66B	Q6_K	3.6 GB	1.00 GB	5.2 GB	5.4 GB free	65	Ollama	Run
Gemma 3 4B	4.3B	Q6_K	3.3 GB	0.86 GB	4.7 GB	5.9 GB free	71	Ollama	Run
Qwen3 4B	4.02B	Q6_K	3.1 GB	4.50 GB	8.2 GB	2.4 GB free	76	Ollama	Run
Ministral 3 3B	3.85B	Q6_K	2.9 GB	3.25 GB	6.8 GB	3.8 GB free	79	Ollama	Run
Phi-4-mini 3.8B	3.84B	Q6_K	2.9 GB	4.00 GB	7.5 GB	3.1 GB free	79	Ollama	Run
Granite 4.1 3B	3.4B	Q6_K	2.6 GB	2.50 GB	5.7 GB	4.9 GB free	90	Ollama	Run
Llama 3.2 3B Instruct	3.21B	Q6_K	2.5 GB	3.50 GB	6.6 GB	4.0 GB free	95	Ollama	Run
LFM2.5 2.6B New	2.7B	Q6_K	2.1 GB	0.50 GB	3.2 GB	7.4 GB free	113	llama.cpp	Run
Qwen3.5 2B	2.27B	Q6_K	1.7 GB	0.38 GB	2.7 GB	7.9 GB free	134	Ollama	Run
Qwen3 1.7B	1.72B	Q6_K	1.3 GB	3.50 GB	5.4 GB	5.2 GB free	177	Ollama	Run
Llama 3.2 1B Instruct	1.24B	Q6_K	0.9 GB	1.00 GB	2.5 GB	8.1 GB free	245	Ollama	Run
Gemma 3 1B	1.0B	Q6_K	0.8 GB	0.14 GB	1.5 GB	9.1 GB free	304	Ollama	Run
Qwen3.5 0.8B	0.87B	Q6_K	0.7 GB	0.38 GB	1.6 GB	9.0 GB free	350	Ollama	Run
Qwen3 0.6B	0.6B	Q6_K	0.5 GB	3.50 GB	4.6 GB	6.0 GB free	507	Ollama	Run

Runs — tight

1 model · fits at 32K, drop context or quant to go longer

Model	Params	Quant	Weights	+KV 32K	Total	VRAM headroom	Tok/s	Runtime
Mistral 7B Instruct v0.3	7.25B	Q6_K	5.5 GB	4.00 GB	10.1 GB	0.5 GB free	42	llama.cpp	Run

Won't fit in VRAM

52 models · some are possible with CPU offload

Model	Params	Quant	Weights	+KV 32K	Total	Over budget	Tok/s	Runtime
gpt-oss 20B	20.9B MoE / 3.6B act	MXFP4	10.8 GB	0.75 GB	12.2 GB	+1.6 GB	~27	llama.cpp	Why
Qwen3 14B	14.8B	Q6_K	11.3 GB	5.00 GB	16.9 GB	+6.3 GB	~5.1	llama.cpp	Why
Phi-4 14B	14.7B	Q6_K	11.2 GB	3.13 GB	15.0 GB	+4.4 GB	~6.7	llama.cpp	Why
Ministral 3 14B	13.9B	Q6_K	10.6 GB	5.00 GB	16.2 GB	+5.6 GB	~5.7	llama.cpp	Why
Gemma 3 12B	12.2B	Q6_K	9.3 GB	2.31 GB	12.2 GB	+1.6 GB	~13	llama.cpp	Why
Mistral NeMo 12B	12.2B	Q6_K	9.3 GB	5.00 GB	14.9 GB	+4.3 GB	~7.1	llama.cpp	Why
Gemma 4 12B	12B	Q6_K	9.2 GB	2.31 GB	12.1 GB	+1.5 GB	~14	llama.cpp	Why
Ministral 3 8B	8.92B	Q6_K	6.8 GB	4.25 GB	11.7 GB	+1.1 GB	~19	llama.cpp	Why
Granite 4.1 8B	8.79B	Q6_K	6.7 GB	5.00 GB	12.3 GB	+1.7 GB	~15	llama.cpp	Why
Qwen3 8B	8.19B	Q6_K	6.3 GB	4.50 GB	11.4 GB	+0.8 GB	~23	llama.cpp	Why
Llama 3.1 8B Instruct	8.03B	Q6_K	6.1 GB	4.00 GB	10.7 GB	+0.1 GB	~34	llama.cpp	Why
Olmo 3 7B Instruct	7.3B	Q6_K	5.6 GB	5.50 GB	11.7 GB	+1.1 GB	~20	llama.cpp	Why
Kimi K3 2.8T-A104B New	2780B MoE / 104B act	Q6_K	2123.0 GB	0.84 GB	2124.5 GB	+2113.9 GB	~0.2	llama.cpp	Why
Qwen3.8 2.4T-A95B New	2446B MoE / 95B act	Q6_K	1868.0 GB	2.88 GB	1871.4 GB	+1860.8 GB	~0.2	llama.cpp	Why
DeepSeek V4 Pro 1.6T-A49B New	1650B MoE / 49B act	Q6_K	1260.1 GB	2.14 GB	1262.8 GB	+1252.2 GB	~0.4	llama.cpp	Why
Kimi K2.6 1T-A32B	1027B MoE / 32B act	Q6_K	784.3 GB	2.14 GB	787.0 GB	+776.4 GB	~0.6	llama.cpp	Why
GLM-5.2 744B-A40B	753B MoE / 40B act	Q6_K	575.1 GB	2.74 GB	578.4 GB	+567.8 GB	~0.5	llama.cpp	Why
DeepSeek-R1 671B	671B MoE / 37B act	Q6_K	512.4 GB	2.14 GB	515.2 GB	+504.6 GB	~0.5	llama.cpp	Why
Qwen3.5 397B-A17B	403B MoE / 17B act	Q6_K	307.8 GB	0.94 GB	309.3 GB	+298.7 GB	~1.1	llama.cpp	Why
Ornith 1.5 397B-A17B New this week	397B MoE / 17B act	Q6_K	303.2 GB	0.94 GB	304.7 GB	+294.1 GB	~1.1	llama.cpp	Why
DeepSeek V4 Flash 284B-A13B New	284B MoE / 13B act	Q6_K	216.9 GB	1.51 GB	219.0 GB	+208.4 GB	~1.5	llama.cpp	Why
Qwen3 235B-A22B	235B MoE / 22B act	Q6_K	179.5 GB	5.88 GB	185.9 GB	+175.3 GB	~0.8	llama.cpp	Why
Qwen3.5 122B-A10B	125B MoE / 10B act	Q6_K	95.5 GB	0.75 GB	96.8 GB	+86.2 GB	~2.0	llama.cpp	Why
Nemotron 3 Super 120B-A12B	124B MoE / 12B act	Q6_K	94.7 GB	0.25 GB	95.5 GB	+84.9 GB	~1.7	llama.cpp	Why
Ling 3.0 Flash 124B-A5B New	124B MoE / 5.1B act	Q6_K	94.7 GB	0.25 GB	95.5 GB	+84.9 GB	~3.9	llama.cpp	Why
Mistral Small 4 119B-A6B	119B MoE / 6.5B act	Q6_K	90.9 GB	0.70 GB	92.2 GB	+81.6 GB	~3.1	llama.cpp	Why
gpt-oss 120B	117B MoE / 5.1B act	MXFP4	60.5 GB	1.13 GB	62.2 GB	+51.6 GB	~6.0	llama.cpp	Why
Llama 4 Scout 109B-A17B	109B MoE / 17B act	Q6_K	83.2 GB	2.63 GB	86.5 GB	+75.9 GB	~1.2	llama.cpp	Why
Llama 3.3 70B Instruct	70.6B	Q6_K	53.9 GB	10.00 GB	64.5 GB	+53.9 GB	~0.7	llama.cpp	Why
DeepSeek-R1-Distill-Llama 70B	70.6B	Q6_K	53.9 GB	10.00 GB	64.5 GB	+53.9 GB	~0.7	llama.cpp	Why
Qwen3.6 35B-A3B	35.9B MoE / 3.3B act	Q6_K	27.4 GB	0.63 GB	28.6 GB	+18.0 GB	~7.8	llama.cpp	Why
Ornith 1.5 35B-A3B New this week	35.9B MoE / 3.3B act	Q6_K	27.4 GB	0.63 GB	28.6 GB	+18.0 GB	~7.8	llama.cpp	Why
LLM-jp 4 33B Thinking New this week	33.2B	Q6_K	25.4 GB	8.00 GB	34.0 GB	+23.4 GB	~1.5	llama.cpp	Why
Qwen3 32B	32.8B	Q6_K	25.0 GB	8.00 GB	33.6 GB	+23.0 GB	~1.6	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 32B	32.8B	Q6_K	25.0 GB	8.00 GB	33.6 GB	+23.0 GB	~1.6	llama.cpp	Why
Qwen2.5-Coder 32B	32.8B	Q6_K	25.0 GB	8.00 GB	33.6 GB	+23.0 GB	~1.6	llama.cpp	Why
Olmo 3.1 32B Instruct	32.2B	Q6_K	24.6 GB	2.75 GB	27.9 GB	+17.3 GB	~2.0	llama.cpp	Why
Nemotron 3.5 Lightning 30B-A3B New	31.6B MoE / 3.2B act	Q6_K	24.1 GB	0.19 GB	24.9 GB	+14.3 GB	~8.7	llama.cpp	Why
Gemma 4 31B	31.3B	Q6_K	23.9 GB	5.78 GB	30.3 GB	+19.7 GB	~1.8	llama.cpp	Why
GLM-4.7-Flash 30B-A3B	31.2B MoE / 3B act	Q6_K	23.8 GB	1.65 GB	26.1 GB	+15.5 GB	~8.7	llama.cpp	Why
Qwen3 30B-A3B	30.5B MoE / 3.3B act	Q6_K	23.3 GB	3.00 GB	26.9 GB	+16.3 GB	~7.4	llama.cpp	Why
Qwen3 Coder 30B-A3B	30.5B MoE / 3.3B act	Q6_K	23.3 GB	3.00 GB	26.9 GB	+16.3 GB	~7.4	llama.cpp	Why
Muse Glimmer 30B New	29.8B	Q6_K	22.8 GB	0.48 GB	23.8 GB	+13.2 GB	~2.5	llama.cpp	Why
Granite 4.1 30B	28.9B	Q6_K	22.1 GB	8.00 GB	30.7 GB	+20.1 GB	~1.8	llama.cpp	Why
Qwen3.8 27B New this week	27.8B	Q6_K	21.2 GB	2.00 GB	23.8 GB	+13.2 GB	~2.5	llama.cpp	Why
Qwen3.6 27B	27.8B	Q6_K	21.2 GB	2.00 GB	23.8 GB	+13.2 GB	~2.5	llama.cpp	Why
Gemma 3 27B	27.4B	Q6_K	20.9 GB	2.91 GB	24.4 GB	+13.8 GB	~2.4	llama.cpp	Why
Gemma 4 26B-A4B	26.5B MoE / 3.8B act	Q6_K	20.2 GB	1.45 GB	22.3 GB	+11.7 GB	~7.5	llama.cpp	Why
Devstral Small 2 24B	24B	Q6_K	18.3 GB	5.00 GB	23.9 GB	+13.3 GB	~2.6	llama.cpp	Why
Mistral Small 3.2 24B	23.6B	Q6_K	18.0 GB	5.00 GB	23.6 GB	+13.0 GB	~2.6	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 14B	14.8B	Q6_K	11.3 GB	6.00 GB	17.9 GB	+7.3 GB	~4.6	llama.cpp	Why
Qwen2.5-Coder 14B	14.8B	Q6_K	11.3 GB	6.00 GB	17.9 GB	+7.3 GB	~4.6	llama.cpp	Why

Totals = quantised weights + f16 KV cache at 32K 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 384 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.