What local LLMs run on RX 7600 8GB?

With 8 GB VRAM, assuming 16 GB system RAM for partial offload, these are the best open models that fit. The top pick is Qwen3 8B at Q4_K_M (~6.2 GB, ~33 tok/s): ollama run qwen3:8b.

Best for coding: Qwen 2.5 Coder 7B (qwen2.5-coder:7b-instruct-q5_K_M), Code Llama 7B (codellama:7b-instruct-q5_K_M), gpt-oss 20B (MoE, MXFP4) (gpt-oss:20b).

Runtimes available for this hardware: Ollama, LM Studio, llama.cpp, vLLM.

Open the interactive checker for RX 7600 8GB

#	Model	Quant	Memory needed	Fit	Speed	Command
1	Qwen3 8B	Q4_K_M	6.2 GB	fits in fast memory	~33 tok/s	`ollama run qwen3:8b`
2	DeepSeek R1 0528 Qwen3 8B	Q4_K_M	6.2 GB	fits in fast memory	~33 tok/s	`ollama run deepseek-r1:8b`
3	DeepSeek R1 Distill Qwen 7B	Q4_K_M	5.7 GB	fits in fast memory	~37 tok/s	`ollama run deepseek-r1:7b`
4	MiniCPM-V 2.6 8B	Q5_K_M	7.5 GB	fits in fast memory	~27 tok/s	`ollama run minicpm-v:8b-2.6-q5_K_M`
5	Qwen 2.5 VL 7B	Q4_K_M	7 GB	fits in fast memory	~29 tok/s	`ollama run qwen2.5vl:7b`
6	Phi-4 Mini 3.8B	Q8_0	4.9 GB	fits in fast memory	~42 tok/s	`ollama run phi4-mini:3.8b-q8_0`
7	Qwen3 4B	Q8_0	5.2 GB	fits in fast memory	~39 tok/s	`ollama run qwen3:4b-q8_0`
8	Llama 3.2 3B	Q8_0	4.2 GB	fits in fast memory	~51 tok/s	`ollama run llama3.2:3b-instruct-q8_0`
9	Gemma 3 4B	Q8_0	5.8 GB	fits in fast memory	~35 tok/s	`ollama run gemma3:4b-it-q8_0`
10	tev1 4B (Together AI, decision)	Q8_0	5.4 GB	fits in fast memory	~38 tok/s	`ollama run tev1:4b-q8_0`
11	Qwen3 1.7B	Q8_0	2.9 GB	fits in fast memory	~79 tok/s	`ollama run qwen3:1.7b-q8_0`
12	DeepSeek R1 Distill Qwen 1.5B	Q8_0	2.6 GB	fits in fast memory	~91 tok/s	`ollama run deepseek-r1:1.5b-qwen-distill-q8_0`

Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-14.

A project by OnDevice Labs · llms.txt