What LLMs can a Radeon RX 9070 XT run?

Your rig

Radeon RX 9070 XT · 16 GB

128 GB system RAM · RDNA 4 · 645 GB/s · 14.4 GB usable VRAM

Which one should I actually run?

Best models for your Radeon RX 9070 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 Q8_0 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.	Q8_0 · 11.1 GB	41	Runs great Run
Best for coding	Qwen3.5 9B Alibaba · Apache 2.0	The best coding model for 8–12 GB cards.	Q8_0 · 11.1 GB	41	Runs great Run
Best reasoning	gpt-oss 20B OpenAI · Apache 2.0	Low/medium/high reasoning effort in 13 GB.	MXFP4 · 12.2 GB	81	Runs great Run
Best for writing	Gemma 4 E4B Google · Apache 2.0	Readable prose on a laptop.	Q8_0 · 9.0 GB	49	Runs great Run
Best vision	Qwen3.5 9B Alibaba · Apache 2.0	Vision on an 8–12 GB card.	Q8_0 · 11.1 GB	41	Runs great Run
Best for agents	gpt-oss 20B OpenAI · Apache 2.0	Harmony-format tool calling, native 4-bit.	MXFP4 · 12.2 GB	81	Runs great Run
Best translation	Qwen3.5 9B Alibaba · Apache 2.0	Strong CJK and European translation in 8–12 GB.	Q8_0 · 11.1 GB	41	Runs great Run
Fastest good model	gpt-oss 20B OpenAI · Apache 2.0	3.6B active, native 4-bit.	MXFP4 · 12.2 GB	81	Runs great Run
Best long context	Qwen3.5 4B Alibaba · Apache 2.0	262K on 8 GB.	Q8_0 · 9.2 GB at 128K context	85	Runs great Run

Everything that fits

Runs great

25 of 76 · fits with headroom for a longer prompt

Model	Params	Quant	Weights	+KV 32K	Total	VRAM headroom	Tok/s	Runtime
gpt-oss 20B	20.9B MoE / 3.6B act	MXFP4	10.8 GB	0.75 GB	12.2 GB	2.2 GB free	81	Ollama	Run
Qwen3.5 9B	9.65B	Q8_0	9.5 GB	1.00 GB	11.1 GB	3.3 GB free	41	Ollama	Run
Ornith 1.5 9B New this week	9.41B	Q8_0	9.3 GB	1.00 GB	10.9 GB	3.5 GB free	42	Ollama	Run
LFM2.5 8B-A1B	8.47B MoE / 1.5B act	Q8_0	8.4 GB	0.38 GB	9.4 GB	5.0 GB free	101	Ollama	Run
Fara 7B	8.29B	Q8_0	8.2 GB	1.75 GB	10.6 GB	3.8 GB free	48	llama.cpp	Run
Gemma 4 E4B	8.0B	Q8_0	7.9 GB	0.47 GB	9.0 GB	5.4 GB free	49	Ollama	Run
Ling 3.0 Tiny 7.9B-A1.3B New	7.9B MoE / 1.3B act	Q8_0	7.8 GB	0.21 GB	8.6 GB	5.8 GB free	117	llama.cpp	Run
DeepSeek-R1-Distill-Qwen 7B	7.62B	Q8_0	7.5 GB	1.75 GB	9.9 GB	4.5 GB free	52	Ollama	Run
Qwen2.5-Coder 7B	7.62B	Q8_0	7.5 GB	1.75 GB	9.9 GB	4.5 GB free	52	Ollama	Run
Mistral 7B Instruct v0.3	7.25B	Q8_0	7.2 GB	4.00 GB	11.8 GB	2.6 GB free	54	Ollama	Run
Gemma 4 E2B	5.1B	Q8_0	5.0 GB	0.23 GB	5.9 GB	8.5 GB free	77	Ollama	Run
Qwen3.5 4B	4.66B	Q8_0	4.6 GB	1.00 GB	6.2 GB	8.2 GB free	85	Ollama	Run
Gemma 3 4B	4.3B	Q8_0	4.3 GB	0.86 GB	5.7 GB	8.7 GB free	92	Ollama	Run
Qwen3 4B	4.02B	Q8_0	4.0 GB	4.50 GB	9.1 GB	5.3 GB free	98	Ollama	Run
Ministral 3 3B	3.85B	Q8_0	3.8 GB	3.25 GB	7.7 GB	6.7 GB free	102	Ollama	Run
Phi-4-mini 3.8B	3.84B	Q8_0	3.8 GB	4.00 GB	8.4 GB	6.0 GB free	103	Ollama	Run
Granite 4.1 3B	3.4B	Q8_0	3.4 GB	2.50 GB	6.5 GB	7.9 GB free	116	Ollama	Run
Llama 3.2 3B Instruct	3.21B	Q8_0	3.2 GB	3.50 GB	7.3 GB	7.1 GB free	123	Ollama	Run
LFM2.5 2.6B New	2.7B	Q8_0	2.7 GB	0.50 GB	3.8 GB	10.6 GB free	146	llama.cpp	Run
Qwen3.5 2B	2.27B	Q8_0	2.2 GB	0.38 GB	3.2 GB	11.2 GB free	174	Ollama	Run
Qwen3 1.7B	1.72B	Q8_0	1.7 GB	3.50 GB	5.8 GB	8.6 GB free	229	Ollama	Run
Llama 3.2 1B Instruct	1.24B	Q8_0	1.2 GB	1.00 GB	2.8 GB	11.6 GB free	318	Ollama	Run
Gemma 3 1B	1.0B	Q8_0	1.0 GB	0.14 GB	1.7 GB	12.7 GB free	395	Ollama	Run
Qwen3.5 0.8B	0.87B	Q8_0	0.9 GB	0.38 GB	1.8 GB	12.6 GB free	454	Ollama	Run
Qwen3 0.6B	0.6B	Q8_0	0.6 GB	3.50 GB	4.7 GB	9.7 GB free	658	Ollama	Run

Runs — tight

5 models · fits at 32K, drop context or quant to go longer

Model	Params	Quant	Weights	+KV 32K	Total	VRAM headroom	Tok/s	Runtime
Ministral 3 8B	8.92B	Q8_0	8.8 GB	4.25 GB	13.7 GB	0.7 GB free	44	llama.cpp	Run
Granite 4.1 8B	8.79B	Q8_0	8.7 GB	5.00 GB	14.3 GB	0.1 GB free	45	llama.cpp	Run
Qwen3 8B	8.19B	Q8_0	8.1 GB	4.50 GB	13.2 GB	1.2 GB free	48	llama.cpp	Run
Llama 3.1 8B Instruct	8.03B	Q8_0	7.9 GB	4.00 GB	12.5 GB	1.9 GB free	49	llama.cpp	Run
Olmo 3 7B Instruct	7.3B	Q8_0	7.2 GB	5.50 GB	13.3 GB	1.1 GB free	54	llama.cpp	Run

Won't fit in VRAM

46 models · some are possible with CPU offload

Model	Params	Quant	Weights	+KV 32K	Total	Over budget	Tok/s	Runtime
Mistral Small 4 119B-A6B	119B MoE / 6.5B act	Q8_0	117.8 GB	0.70 GB	119.1 GB	+104.7 GB	~2.4	llama.cpp	Why
gpt-oss 120B	117B MoE / 5.1B act	MXFP4	60.5 GB	1.13 GB	62.2 GB	+47.8 GB	~6.5	llama.cpp	Why
Llama 4 Scout 109B-A17B	109B MoE / 17B act	Q8_0	107.9 GB	2.63 GB	111.1 GB	+96.7 GB	~0.9	llama.cpp	Why
Llama 3.3 70B Instruct	70.6B	Q8_0	69.9 GB	10.00 GB	80.5 GB	+66.1 GB	~0.5	llama.cpp	Why
DeepSeek-R1-Distill-Llama 70B	70.6B	Q8_0	69.9 GB	10.00 GB	80.5 GB	+66.1 GB	~0.5	llama.cpp	Why
Qwen3.6 35B-A3B	35.9B MoE / 3.3B act	Q8_0	35.5 GB	0.63 GB	36.7 GB	+22.3 GB	~6.4	llama.cpp	Why
Ornith 1.5 35B-A3B New this week	35.9B MoE / 3.3B act	Q8_0	35.5 GB	0.63 GB	36.7 GB	+22.3 GB	~6.4	llama.cpp	Why
LLM-jp 4 33B Thinking New this week	33.2B	Q8_0	32.9 GB	8.00 GB	41.5 GB	+27.1 GB	~1.3	llama.cpp	Why
Qwen3 32B	32.8B	Q8_0	32.5 GB	8.00 GB	41.1 GB	+26.7 GB	~1.3	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 32B	32.8B	Q8_0	32.5 GB	8.00 GB	41.1 GB	+26.7 GB	~1.3	llama.cpp	Why
Qwen2.5-Coder 32B	32.8B	Q8_0	32.5 GB	8.00 GB	41.1 GB	+26.7 GB	~1.3	llama.cpp	Why
Olmo 3.1 32B Instruct	32.2B	Q8_0	31.9 GB	2.75 GB	35.2 GB	+20.8 GB	~1.7	llama.cpp	Why
Nemotron 3.5 Lightning 30B-A3B New	31.6B MoE / 3.2B act	Q8_0	31.3 GB	0.19 GB	32.1 GB	+17.7 GB	~7.3	llama.cpp	Why
Gemma 4 31B	31.3B	Q8_0	31.0 GB	5.78 GB	37.4 GB	+23.0 GB	~1.5	llama.cpp	Why
GLM-4.7-Flash 30B-A3B	31.2B MoE / 3B act	Q8_0	30.9 GB	1.65 GB	33.1 GB	+18.7 GB	~7.3	llama.cpp	Why
Qwen3 30B-A3B	30.5B MoE / 3.3B act	Q8_0	30.2 GB	3.00 GB	33.8 GB	+19.4 GB	~6.3	llama.cpp	Why
Qwen3 Coder 30B-A3B	30.5B MoE / 3.3B act	Q8_0	30.2 GB	3.00 GB	33.8 GB	+19.4 GB	~6.3	llama.cpp	Why
Muse Glimmer 30B New	29.8B	Q8_0	29.5 GB	0.48 GB	30.6 GB	+16.2 GB	~2.1	llama.cpp	Why
Granite 4.1 30B	28.9B	Q8_0	28.6 GB	8.00 GB	37.2 GB	+22.8 GB	~1.6	llama.cpp	Why
Qwen3.8 27B New this week	27.8B	Q8_0	27.5 GB	2.00 GB	30.1 GB	+15.7 GB	~2.2	llama.cpp	Why
Qwen3.6 27B	27.8B	Q8_0	27.5 GB	2.00 GB	30.1 GB	+15.7 GB	~2.2	llama.cpp	Why
Gemma 3 27B	27.4B	Q8_0	27.1 GB	2.91 GB	30.6 GB	+16.2 GB	~2.1	llama.cpp	Why
Gemma 4 26B-A4B	26.5B MoE / 3.8B act	Q8_0	26.2 GB	1.45 GB	28.3 GB	+13.9 GB	~6.5	llama.cpp	Why
Devstral Small 2 24B	24B	Q8_0	23.7 GB	5.00 GB	29.3 GB	+14.9 GB	~2.3	llama.cpp	Why
Mistral Small 3.2 24B	23.6B	Q8_0	23.4 GB	5.00 GB	29.0 GB	+14.6 GB	~2.4	llama.cpp	Why
Qwen3 14B	14.8B	Q8_0	14.6 GB	5.00 GB	20.2 GB	+5.8 GB	~5.5	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 14B	14.8B	Q8_0	14.6 GB	6.00 GB	21.2 GB	+6.8 GB	~4.8	llama.cpp	Why
Qwen2.5-Coder 14B	14.8B	Q8_0	14.6 GB	6.00 GB	21.2 GB	+6.8 GB	~4.8	llama.cpp	Why
Phi-4 14B	14.7B	Q8_0	14.5 GB	3.13 GB	18.3 GB	+3.9 GB	~7.5	llama.cpp	Why
Ministral 3 14B	13.9B	Q8_0	13.8 GB	5.00 GB	19.4 GB	+5.0 GB	~6.3	llama.cpp	Why
Gemma 3 12B	12.2B	Q8_0	12.1 GB	2.31 GB	15.0 GB	+0.6 GB	~22	llama.cpp	Why
Mistral NeMo 12B	12.2B	Q8_0	12.1 GB	5.00 GB	17.7 GB	+3.3 GB	~8.9	llama.cpp	Why
Gemma 4 12B	12B	Q8_0	11.9 GB	2.31 GB	14.8 GB	+0.4 GB	~25	llama.cpp	Why
Kimi K3 2.8T-A104B New	2780B MoE / 104B act	Q8_0	2750.9 GB	0.84 GB	2752.3 GB	+2737.9 GB	~0.1	llama.cpp	Why
Qwen3.8 2.4T-A95B New	2446B MoE / 95B act	Q8_0	2420.4 GB	2.88 GB	2423.9 GB	+2409.5 GB	~0.1	llama.cpp	Why
DeepSeek V4 Pro 1.6T-A49B New	1650B MoE / 49B act	Q8_0	1632.7 GB	2.14 GB	1635.5 GB	+1621.1 GB	~0.3	llama.cpp	Why
Kimi K2.6 1T-A32B	1027B MoE / 32B act	Q8_0	1016.2 GB	2.14 GB	1019.0 GB	+1004.6 GB	~0.4	llama.cpp	Why
GLM-5.2 744B-A40B	753B MoE / 40B act	Q8_0	745.1 GB	2.74 GB	748.5 GB	+734.1 GB	~0.4	llama.cpp	Why
DeepSeek-R1 671B	671B MoE / 37B act	Q8_0	664.0 GB	2.14 GB	666.7 GB	+652.3 GB	~0.4	llama.cpp	Why
Qwen3.5 397B-A17B	403B MoE / 17B act	Q8_0	398.8 GB	0.94 GB	400.3 GB	+385.9 GB	~0.9	llama.cpp	Why
Ornith 1.5 397B-A17B New this week	397B MoE / 17B act	Q8_0	392.8 GB	0.94 GB	394.4 GB	+380.0 GB	~0.9	llama.cpp	Why
DeepSeek V4 Flash 284B-A13B New	284B MoE / 13B act	Q8_0	281.0 GB	1.51 GB	283.1 GB	+268.7 GB	~1.1	llama.cpp	Why
Qwen3 235B-A22B	235B MoE / 22B act	Q8_0	232.5 GB	5.88 GB	239.0 GB	+224.6 GB	~0.7	llama.cpp	Why
Qwen3.5 122B-A10B	125B MoE / 10B act	Q8_0	123.7 GB	0.75 GB	125.0 GB	+110.6 GB	~1.6	llama.cpp	Why
Nemotron 3 Super 120B-A12B	124B MoE / 12B act	Q8_0	122.7 GB	0.25 GB	123.6 GB	+109.2 GB	~1.3	llama.cpp	Why
Ling 3.0 Flash 124B-A5B New	124B MoE / 5.1B act	Q8_0	122.7 GB	0.25 GB	123.5 GB	+109.1 GB	~3.1	llama.cpp	Why

Totals = quantised weights + f16 KV cache at 32K tokens + 0.6 GB runtime overhead, against 14.4 GB usable VRAM (16 GB less display and driver reserve). Tokens per second are estimated from 645 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.