Back to search results
gemma-4-12B-it · IQ2_XS
AMD Radeon RX 7900 XTX24GBllama.cpp v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_XS) on AMD Radeon RX 7900 XTX with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
97.1 tok/s
Decode
Decode speed
483.73 tok/s
Prefill
Prefill speed
0.81 s
TTFT
Time to first token
14.2 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 (current)Decode 97.1 · Prefill 483.73 ·
- llama.cpp · Q5_K_M 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)
- 97.1 tok/s
- Prefill (avg)
- 483.73 tok/s
- TTFT (avg)
- 0.81 s
- VRAM (avg)
- 14.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.78 GB
- Power draw
- 215.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- IQ2_XS
- Framework
- llama.cpp
- Version
- v0.37
- Context length
- 2048 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)
- 14.2 GB
- OS
- Ubuntu 22.04
- Driver
- amdgpu 6.12
- CUDA
- 12.4
- Power draw
- 215.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Ubuntu 22.04 · CUDA 12.4 · 2048 ctx
97.1 tok/s
Decode
483.73 tok/s
Prefill
0.81 s
TTFT
14.2 GB
VRAM
—
MTP
215.2 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=11 running model_id=65 at IQ2_XS