RX 7600 XT LLM benchmarks
52 results · 124 measurements · 5 sources
Device specifications
| Variant | Memory | Memory type | Bus | Bandwidth | FP16 matrix | INT8 matrix |
|---|---|---|---|---|---|---|
| RX 7600 XT ↗ | 16 GB | GDDR6 | 128-bit | 288 GB/s | 45.1 TFLOPS | 45.1 TOPS |
Manufacturer specifications. Shared system RAM is not dedicated VRAM. Unreported values remain —; measured LLM results retain their reported configuration.
Selected reported tests
24 of 52 resultsSource-reported results, selected across reports by documentation quality. Match configurations before comparing values.
| View Reportllm-bench.io | gmcoder | llm-bench.io QualityFour sequential scenarios: agent workflow, code generation, role play, research | 76.08 / 100LLM judge · Mean | 374.16 tok/sPrefill · mean · per request | 41.69 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View ReportGeneric LLM | Ornith-1.5-35B-A3B | Token speed | — | 342 tok/sPrefill · per request | 38.8 tok/sGeneration · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Muse-Glimmer-30B | Token speed | — | ~308 tok/sPrefill · per request | ~20 tok/sGeneration · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | 1,099.64 tok/sPrefill · mean · per request | — | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | 840.85 tok/sPrefill · mean · per request | — | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View Reportllm-bench.io | ornith-1.5-9b@q6_k | llm-bench.io QualityFour sequential scenarios: agent workflow, code generation, role play, research | 73.71 / 100LLM judge · Mean | 732.23 tok/sPrefill · mean · per request | 39.8 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Ornith-1.5-35B-A3B | Token speed | — | 328 tok/sPrefill · per request | 40.9 tok/sGeneration · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | — | 48.58 tok/sGeneration · mean · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | — | 53.02 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View Reportllm-bench.io | ornith-1.5-9b@q6_k | llm-bench.io QualityFour sequential scenarios: agent workflow, code generation, role play, research | 63.25 / 100LLM judge · Mean | 756.41 tok/sPrefill · mean · per request | 39.11 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Ornith-1.5-35B-A3B | Token speed | — | 271 tok/sPrefill · per request | 20.2 tok/sGeneration · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | 1,199.16 tok/sPrefill · mean · per request | — | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | 1,024.38 tok/sPrefill · mean · per request | — | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View Reportllm-bench.io | qwen3.5-9b-mtp@q4_k_xl (checkpoint unspecified) | llm-bench.io QualityFour sequential scenarios: agent workflow, code generation, role play, research | 68.8 / 100LLM judge · Mean | 219.05 tok/sPrefill · mean · per request | 47.69 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Ornith-1.5-35B-A3B | Token speed | — | 353 tok/sPrefill · per request | 42.5 tok/sGeneration · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | — | 47.65 tok/sGeneration · mean · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | — | 56.11 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View Reportllm-bench.io | qwen3.5-9b-mtp@q6_k (checkpoint unspecified) | llm-bench.io QualityFour sequential scenarios: agent workflow, code generation, role play, research | 68.45 / 100LLM judge · Mean | 756.46 tok/sPrefill · mean · per request | 44.9 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Ornith-1.5-35B-A3B | Token speed | — | — | ~33.2 tok/sGeneration · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | 606.24 tok/sPrefill · mean · per request | — | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllm-bench.io | qwen3.5-9b-mtp@q8_0 (checkpoint unspecified) | llm-bench.io QualityFour sequential scenarios: agent workflow, code generation, role play, research | 68.35 / 100LLM judge · Mean | — | 38.83 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Ornith-1.5-35B-A3B | Token speed | — | — | ~45.9 tok/sGeneration · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | — | 52.84 tok/sGeneration · mean · per request | 1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View Reportllm-bench.io | qwen3.5-9b-mtp@q8_0 (checkpoint unspecified) | llm-bench.io QualityFour sequential scenarios: agent workflow, code generation, role play, research | 67.39 / 100LLM judge · Mean | 857.02 tok/sPrefill · mean · per request | 41.48 tok/sGeneration · mean · per request | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
Models and software in this collection
Model families: Gemma 4, Llama 2, Muse Glimmer, Qwen3.5, Qwen3.6, Qwen3.8
Engines: LM Studio, Strata / llama.cpp, llama.cpp
Methodology and evidence standards · Download the research dataset