AMD · RDNA 3 · 8 GB VRAM tier
Best AI Models for AMD Radeon RX 7600 (8 GB)
Runs 7–9B models well; 14B doesn't fit in 8 GB.
| # | 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 | MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 90.9 t/s | 90.9 tok/s | Q4_K_M · 2.5 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 |
The RX 7600 is an entry card in the 8 GB class: it runs 7–9B models well. It is power-hungry for its speed, and at its $269 MSRP it gave the best speed per dollar of the cards compared. RDNA 3 generation, released 2023.
RX 7600 strengths and weaknesses
Strengths
- Runs 7–9B models: Qwen3.5 9B at 27.2 tok/s in 6.6 GB
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 8.3 s for the first token
- ROCm, not CUDA: No FP8 weights; MXFP4 only through llama.cpp, not vLLM
Speed per dollar and per watt
On Qwen3.5 9B (9B params) at Q4_K_M. New prices are compared with new, used with used. The last two columns are the speed you get per $100 of price and per 100 W of board power; higher is better. The RX 7600 has no current price, so it is shown at its MSRP.
| Card | New price | tok/s | tok/s per $100 | tok/s per 100 W |
|---|---|---|---|---|
RX 76008 GB | about $269 | 27.2 | 10.1 | 16.5 |
RTX 50608 GBBest new value | about $460 | 45.8 | 10.0 | 31.6 |
RTX 507012 GB | about $840 | 68.7 | 8.2 | 27.5 |
RTX 40608 GB | about $520 | 27.8 | 5.3 | 24.2 |
| Card | Used price | tok/s | tok/s per $100 | tok/s per 100 W |
|---|---|---|---|---|
RTX 50608 GBBest used value | about $388 | 45.8 | 11.8 | 31.6 |
RTX 3060 12GB12 GB | about $329 | 36.8 | 11.2 | 21.6 |
RTX 507012 GB | about $736 | 68.7 | 9.3 | 27.5 |
RTX 407012 GB | about $575 | 51.5 | 9.0 | 25.8 |
RTX 40608 GB | about $335 | 27.8 | 8.3 | 24.2 |
RTX 4060 Ti 8GB8 GB | about $362 | 29.4 | 8.1 | 18.4 |
RTX 4070 SUPER12 GB | about $675 | 51.5 | 7.6 | 23.4 |
RTX 4070 Ti12 GB | about $722 | 51.5 | 7.1 | 18.1 |
Cost per token: the RX 7600 against 8–12 GB cards
On Qwen3.5 9B (9B params, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.
- Card, MSRP
- $0.63
- Power
- $0.25
Renting costs as much as buying after ≈1,400 hours (≈0.9 years at 4 h a day).
Each dot is a card; hover or tap it for its numbers, click to open it. Cards without a price for the chosen basis are left out. How we calculate cost per token
Cards people weigh against the RX 7600, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.
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 822 models on the RX 7600
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 |
|---|---|---|---|---|---|---|
InternVL3 1BVision | Q4_K_M | 2.0 GB | 278.7 t/s | — | S100, Runs great | |
| Q4_K_M | 1.3 GB | 174.5 t/s | 131K | S98, Runs great | ||
VibeThinker 3BChatMathCodeReasoning | Q4_K_M | 2.8 GB | 77.5 t/s | 131K | S87, Runs great | |
| Q4_K_M | 2.7 GB | 64.0 t/s | 131K | A84, Runs well | ||
Unlimited OCR 2Vision | Q4_K_M | 3.3 GB | 138.3 t/s | 131K | S96, Runs great | |
Qwen3 0.6BChat | Q4_K_M | 1.6 GB | 432.0 t/s | — | S100, Runs great | |
HRM Text 1BChat | BF16 | 3.1 GB | 60.2 t/s | 4K | A84, Runs well | |
| BF16 | 0.0 GB | 17280.0 t/s | 0K | S100, Runs great | ||
| Q4_K_M | 1.2 GB | 161.5 t/s | 128K | S97, Runs great | ||
The GuageLLM 23MChat | Q4_K_M | 0.0 GB | 8640.0 t/s | 0K | S100, Runs great | |
Chandra Ocr 2VisionFunctions | Q4_K_M | 3.8 GB | 47.3 t/s | 262K | A79, Runs well | |
| Q4_K_M | 4 GB | 48.7 t/s | 262K | A79, Runs well | ||
OneRec 1.7BChatFunctions | Q4_K_M | 3.5 GB | 95.5 t/s | 41K | S90, Runs great | |
SmolVLM 500M InstructVision | Q4_K_M | 0.9 GB | 250.4 t/s | 8K | S100, Runs great | |
Gemma 4 E4B IT OBLITERATEDChatFunctions | Q4_K_M | 5.6 GB | 32.5 t/s | 131K | A72, Runs well |
Specs
- Architecture
- RDNA 3
- VRAM
- 8 GB GDDR6
- Memory bandwidth
- 288.0 GB/s
- FP16 (dense)
- 43.50 TFLOPS
- Stream processors
- 2,048
- TDP
- 165 W
- Released
- 2023-05-25
- MSRP
- $269
RX 7600 FAQ
Is the RX 7600 still worth it in 2026?
At its MSRP of $269 you get 10.1 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 4 cards compared here; it is also the 9th fastest out of 12 cards with 8 GB. It runs 7–9B models well; 14B doesn't fit in 8 GB.
What is the largest model the RX 7600 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 7600 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 7600 give?
About 27.2 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 8.3 s on a 4K-token prompt.
What power supply does the RX 7600 need?
Plan a 350 W PSU (2× the 165 W TDP).
Is renting cheaper than buying an RX 7600?
An RTX 3090 (24 GB) rents from $0.20/hr. Renting costs as much as buying after ≈1,400 hours (≈0.9 years at 4 h a day).