AMD · RDNA 3 · 8 GB VRAM tier
Best AI Models for AMD Radeon RX 7600M XT (8 GB)
Runs 7–9B models well; 14B doesn't fit in 8 GB.
8 GB GDDR6288 GB/s43 TFLOPS FP16120 WRDNA 3 2023
8 GB at 288 GB/s: ~7-8B Q4 models, no more. Not on AMD's official ROCm list; the Vulkan backend (llama.cpp, LM Studio) is the easy path.
| # | Model | Speed | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.2 t/s | 27.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 53.0 t/s | 53.0 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 28.3 t/s | 28.3 tok/s | Q4_K_M · 7.3 GB | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 60.8 t/s | 60.8 tok/s | Q4_K_M · 5.0 GB | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 97.9 t/s | 97.9 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Reasoning Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.2 t/s | 27.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 60.8 t/s | 60.8 tok/s | Q4_K_M · 5.0 GB | |
| 3 | Qwen2.5 7B InstructAlibaba Q4_K_M · 5.8 GB · 34.6 t/s | 34.6 tok/s | Q4_K_M · 5.8 GB | |
| 4 | Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 28.3 t/s | 28.3 tok/s | overall | Q4_K_M · 7.3 GB |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 97.9 t/s | 97.9 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Long context Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 53.0 t/s | 53.0 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 27.2 t/s | 27.2 tok/s | Q4_K_M · 6.6 GB | |
| 3 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 32.5 t/s | 32.5 tok/s | Q4_K_M · 5.6 GB | |
| 4 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 97.9 t/s | 97.9 tok/s | Q4_K_M · 5.5 GB | |
| 5 | Spark X2.6 4BXHToken Q4_K_M · 4.3 GB · 58.4 t/s | 58.4 tok/s | Q4_K_M · 4.3 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 53.0 t/s | 53.0 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 97.9 t/s | 97.9 tok/s | Q4_K_M · 5.5 GB | |
| 3 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 32.5 t/s | 32.5 tok/s | Q4_K_M · 5.6 GB | |
| 4 | Q4_K_M · 6.5 GB · 27.8 t/s | 27.8 tok/s | Q4_K_M · 6.5 GB | |
| 5 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 27.2 t/s | 27.2 tok/s | Q4_K_M · 6.6 GB |
| # | Model | Speed | Vision Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.2 t/s | 27.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 53.0 t/s | 53.0 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 60.8 t/s | 60.8 tok/s | Q4_K_M · 5.0 GB | |
| 4 | Q4_K_M · 6.5 GB · 27.8 t/s | 27.8 tok/s | Q4_K_M · 6.5 GB | |
| 5 | MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 135 t/s | 135 tok/s | Q4_K_M · 1.6 GB |
See all 218 models on the RX 7600M XT →Best quant that fits · speeds estimated on this card
The RX 7600M XT runs 7–9B models well. RDNA 3 generation, released 2023.
GenerationRDNA 3released 2023
RX 7600M XT strengths and weaknesses
Strengths
- Runs 7–9B models: Qwen3.5 9B at 27.2 tok/s in 6.6 GB
- Low power draw: 120 W board power; a 250 W PSU is enough
Weaknesses
- 14B models don't fit: Qwen3 14B needs 11.9 GB at Q4 vs 8 GB here
- Little room for context: Qwen3.5 9B uses 6.6 of 8 GB, 1.4 GB left
- Slow prompt reading: A 4K-token prompt on Qwen3.5 9B waits 8.4 s for the first token
- ROCm, not CUDA: No FP8 weights; MXFP4 only through llama.cpp, not vLLM
Cards people weigh against the RX 7600M XT, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.
4 GB more and 35% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere
▲ 35% speed▲ 4 GBabout $329rent $0.06/hr
68% faster, same 8 GBRTX 5060NVIDIA · 8 GB · Blackwell▲ 68% speedsame 8 GBabout $460
4 GB more and 50% fasterRX 9070 GREAMD · 12 GB · RDNA 4▲ 50% speed▲ 4 GBabout $549
2 GB more and 10% fasterB570Intel · 10 GB · Xe2 (Battlemage), BMG-G21▲ 10% speed▲ 2 GBabout $219
8 GB more and 2.7× the speedRTX 4080NVIDIA · 16 GB · Ada Lovelace▲ 169% speed▲ 8 GBabout $1,199rent $0.27/hr
8 GB more and 2.8× the speedRTX 4080 SUPERNVIDIA · 16 GB · Ada Lovelace▲ 176% speed▲ 8 GBabout $999rent $0.22/hr
Output speed depends on memory bandwidth (288 GB/s). Grey rows need more than 8 GB.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB27.2tok/s
- 14BQwen3 14B · not at 4-bitneeds 11.9 GB
- 27–31BQwen3.8 27B · not at 4-bitneeds 17.9 GB
- 35B MoEQwen3.6 35B A3B · not at 4-bitneeds 22.0 GB
- 70BLlama 3.3 70B Instruct · not at 4-bitneeds 51.3 GB
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 842 models on the RX 7600M XT
Featured onlyBest quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
| Q4_K_M | 7.1 GB | 33.2 t/s | 33K | B60, Decent | ||
Gemma 3 12B ITVision | IQ2_M | 7.4 GB | 38.2 t/s | 33K | B55, Decent | |
| Q4_K_M | 7.3 GB | 36.3 t/s | — | B58, Decent | ||
Glm 4 9B ChatChatFunctions | Q3_K_L | 8.0 GB | 32.6 t/s | 131K | C41, Usable | |
MN 12B Mag Mell R1ChatReasoning | IQ2_M | 7.8 GB | 35.6 t/s | 1024K | B47, Decent | |
| IQ2_M | 7.8 GB | 35.6 t/s | 1024K | B47, Decent | ||
Codegemma 7B ITChatCode | Q4_K_S | 7.9 GB | 32.7 t/s | — | C42, Usable | |
Qwen 7B ChatChat | Q4_K_M | 7.6 GB | 33.9 t/s | 33K | B48, Decent | |
GPT Neox 20BChat | IQ2_M | 7.7 GB | 22.4 t/s | 2K | C38, Usable | |
| IQ2_M | 7.8 GB | 35.8 t/s | — | B47, Decent | ||
| Q2_K | 7.3 GB | 74.8 t/s | 8K | A69, Runs well | ||
| Q4_K_M | 7.9 GB | 31.2 t/s | 131K | C42, Usable | ||
Gemma 3 12B PtVision | IQ2_M | 7.4 GB | 38.2 t/s | — | B55, Decent | |
| Q4_K_M | 7.9 GB | 31.2 t/s | 131K | C42, Usable | ||
Qwen2.5 14B InstructChatFunctions | IQ2_XS | 8.0 GB | 33.7 t/s | 33K | C42, Usable |
Specs
- Architecture
- RDNA 3
- VRAM
- 8 GB GDDR6
- Memory bandwidth
- 288.0 GB/s
- FP16 (dense)
- 42.84 TFLOPS
- Stream processors
- 2,048
- TDP
- 120 W
- Released
- 2023-01-04
RX 7600M XT FAQ
What is the largest model the RX 7600M XT can run?
Qwen3.5 9B (9.7B) is the largest at 4-bit or better: at Q4_K_M it uses 6.6 GB of 8 GB, and runs at about 27.2 tok/s.
Can the RX 7600M XT run 14B models?
No. Qwen3 14B needs 11.9 GB at Q4, more than the 8 GB on this card.
How many tokens per second does the RX 7600M XT give?
About 27.2 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 8.4 s on a 4K-token prompt.
What power supply does the RX 7600M XT need?
Plan a 250 W PSU (2× the 120 W TDP).
Is renting cheaper than buying an RX 7600M XT?
An RTX 5080 (16 GB) rents from $0.22/hr. With regular daily use, owning pays off.