AMD Radeon RX 7600 XT
16 GB · 288 GB/s · 190 W
In short
The AMD Radeon RX 7600 XT has 16 GB of GDDR6 memory with 288 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 52 of the 113 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q6_K, at about 6 tok/s (estimated). The AMD Radeon RX 7600 XT is not on sale new in the UK right now; used, it starts at £348 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the UK, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayGIGABYTE Gaming OC Radeon RX 7600 XT 16GB GDDR6 PCIe HDMI/DP VR Ready | used, asking price | £348+ £7 delivery | In stock | 2 h ago | Buy |
What two of them run
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q6_K | fits | 25.9 GB | 98k172k with q8 cache | 6tok/sest. | 254 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 30.3 GB | 34k59k with q8 cache | 5tok/sest. | 254 tok/s | – |
| Gemma 4 31B | Q6_K | fits | 28.2 GB | 57k110k with q8 cache | 6tok/sest. | 226 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 29.5 GB | 68k107k with q8 cache | 30tok/sest. | 1814 tok/s | chat, coding, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 30.3 GB | 34k59k with q8 cache | 5tok/sest. | 254 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.3 GB | 153k245k with q8 cache | 19tok/sest. | 1614 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 29.0 GB | 85k133k with q8 cache | 30tok/sest. | 1814 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 26.1 GB | 106k183k with q8 cache | 16tok/sest. | 947 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.8 GB | 35k64k with q8 cache | 5tok/sest. | 268 tok/s | – |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 29.8 GB | 78k107k with q8 cache | 44tok/sest. | 1563 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.5 GB | 128k | 29tok/sest. | 1354 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 27.9 GB | 57k102k with q8 cache | 17tok/sest. | 834 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | fits | 27.9 GB | 40k | 6tok/sest. | 158 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 14.1 GB | 256k | 12tok/sest. | 589 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 11.4 GB | 256k | 15tok/sest. | 734 tok/s | chat |
| Gemma 3 27B | Q6_K | fits | 25.0 GB | 95k128k with q8 cache | 6tok/sest. | 270 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | fits | 28.0 GB | 41k76k with q8 cache | 6tok/sest. | 181 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.8 GB | 35k64k with q8 cache | 5tok/sest. | 268 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.9 GB | 97k176k with q8 cache | 8tok/sest. | 408 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 21.1 GB | 40k | 8tok/sest. | 367 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 14.1 GB | 128k | 12tok/sest. | 605 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 14.1 GB | 40k | 12tok/sest. | 605 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 22.2 GB | 16k | 7tok/sest. | 369 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.7 GB | 256k | 28tok/sest. | 1374 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 14.1 GB | 149k256k with q8 cache | 12tok/sest. | 584 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 15.2 GB | 125k128k with q8 cache | 11tok/sest. | 556 tok/s | – |
| Gemma 4 E4B | Q8_0 | fits | 10.0 GB | 128k | 17tok/sest. | 922 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 11.4 GB | 125k | 36tok/sest. | 3017 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 11.6 GB | 128k | 15tok/sest. | 639 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.4 GB | 32k | 170tok/sest. | 6570 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.6 GB | 256k | 128tok/sest. | 6171 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.2 GB | 256k | 85tok/sest. | 2942 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.1 GB | 128k | 56tok/sest. | 2472 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 5.3 GB | 128k | 39tok/sest. | 1476 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 6.0 GB | 128k | 32tok/sest. | 1672 tok/s | chat, coding, agents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 6.0 GB | 32k | 32tok/sest. | 1533 tok/s | chat, coding, agents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.0 GB | 128k | 30tok/sest. | 2178 tok/s | chat, coding, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 7.4 GB | 128k | 25tok/sest. | 1071 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 7.6 GB | 128k | 24tok/sest. | 1123 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 19.0 GB | 128k | 22tok/sest. | 1637 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 27.7 GB | 63k113k with q8 cache | 20tok/sest. | 1681 tok/s | chat |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.8 GB | 128k | 16tok/sest. | 722 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 12.1 GB | 128k | 14tok/sest. | 503 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 13.4 GB | 128k | 12tok/sest. | 639 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.7 GB | 64k | 12tok/sest. | 503 tok/s | – |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 14.1 GB | 149k256k with q8 cache | 12tok/sest. | 584 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 22.1 GB | 74k128k with q8 cache | 7tok/sest. | 345 tok/s | – |
| granite 4.2 30b IBM | Q5_K_M | fits | 29.1 GB | 37k68k with q8 cache | 5tok/sest. | 208 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 29.8 GB | 35k64k with q8 cache | 5tok/sest. | 272 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 29.8 GB | 35k40k with q8 cache | 5tok/sest. | 272 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 29.8 GB | 35k40k with q8 cache | 5tok/sest. | 272 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 29.8 GB | 35k64k with q8 cache | 5tok/sest. | 268 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 41.3 GB | – | 14tok/sest. | 498 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.5 GB | – | 17tok/sest. | 1115 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.8 GB | – | 9tok/sest. | 445 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.6 GB | – | 21tok/sest. | 566 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 49.4 GB | – | 4tok/sest. | 169 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.5 GB | – | 21tok/sest. | 1327 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.3 GB | – | 22tok/sest. | 1921 tok/s | chat, coding, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 51.1 GB | – | 2tok/sest. | 64 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 51.1 GB | – | 2tok/sest. | 64 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 94.4 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.8 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 79.4 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 61.1 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 380.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.8 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 380.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 381.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 381.2 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.8 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.6 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 136.2 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 66.5 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.8 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.6 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 424.2 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 438.1 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.6 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 582.2 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 582.2 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 582.2 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 138.1 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 138.1 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 124.5 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 252.0 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 82.2 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Radeon RX 7600 XT
- Memory
- 16 GB GDDR6
- Memory bus
- 128-bit
- Memory bandwidth
- 288 GB/s
- FP16 compute
- 45 TFLOPS
- Software
- ROCm
- Board power
- 190 W
- PCIe generation
- Gen 4
- PCIe lanes
- x8
Compare with
Questions
- How much memory does the AMD Radeon RX 7600 XT have for AI models?
- The AMD Radeon RX 7600 XT has 16 GB of GDDR6 memory with 288 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the AMD Radeon RX 7600 XT can run locally?
- Qwen 3.8 27B (Q6_K) fits fully in its memory at 32k context and generates at about 6 tok/s, an estimate from its memory bandwidth. 52 of the 113 models we track fit at that context.
- Can the AMD Radeon RX 7600 XT run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the AMD Radeon RX 7600 XT and system RAM can hold.
- How much does the AMD Radeon RX 7600 XT cost in the UK?
- The AMD Radeon RX 7600 XT is not on sale new in the UK right now; used, it starts at £348 (asking price).
Speeds on this page are for 32k context. See the best hardware for local AI at every budget.