Back to search results
gemma-4-12B-it · Q5_K_M
AMD Radeon RX 7900 XTX24GBllama.cpp v0.41L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-12B-it (Q5_K_M) on AMD Radeon RX 7900 XTX with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
54.12 tok/s
Decode
Decode speed
201.79 tok/s
Prefill
Prefill speed
1.59 s
TTFT
Time to first token
22.8 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ2_XS Decode 97.1 · Prefill 483.73 ·
- llama.cpp · Q5_K_M (current)Decode 54.12 · Prefill 201.79 ·
- Strata · IQ2_M Decode 125.31 · Prefill 624.12 ·
- vLLM · Q4_K_S Decode 86.73 · Prefill 462.81 ·
- vLLM · Q5_K_S Decode 64.98 · Prefill 291.13 ·
- Ollama · IQ2_M Decode 92.49 · Prefill 473.64 ·
- Ollama · Q4_K_S Decode 67.64 · Prefill 313.4 ·
- Strata · IQ3_XS Decode 129.13 · Prefill 417.63 ·
Core figures
- Decode (avg)
- 54.12 tok/s
- Prefill (avg)
- 201.79 tok/s
- TTFT (avg)
- 1.59 s
- VRAM (avg)
- 22.8 GB
- MTP acceptance rate
- —
- TTFB
- 0.43 GB
- Power draw
- 247.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- Q5_K_M
- Framework
- llama.cpp
- Version
- v0.41
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Radeon RX 7900 XTX
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 22.8 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu 6.12
- CUDA
- 12.4
- Power draw
- 247.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.41 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx
54.12 tok/s
Decode
201.79 tok/s
Prefill
1.59 s
TTFT
22.8 GB
VRAM
—
MTP
247.3 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=11 running model_id=65 at Q5_K_M