Back to search results
gemma-4-12B-it · Q8_0
NVIDIA RTX 309024GBvLLM 0.7.3L0 Self-reported
This page aggregates 1 real-world runs of gemma-4-12B-it (Q8_0) on NVIDIA RTX 3090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
61.2 tok/s
Decode
Decode speed
459 tok/s
Prefill
Prefill speed
0.22 s
TTFT
Time to first token
13.5 GB
VRAM
VRAM usage
L0 Self-reported
1
Measured runs
1
Independent sources
Other
Source platforms
2026-10-06
Last verified
Performance
- llama.cpp · Q4_K_M Decode 79.26 · Prefill 473.41 ·
- Ollama · Q3_K_L Decode 64.09 · Prefill 302.97 ·
- vLLM · Q6_K Decode 50.6 · Prefill 208.67 ·
- Ollama · IQ3_XS Decode 67.34 · Prefill 278.97 ·
- vLLM · Q4_K_M Decode 100.66 · Prefill 612.88 ·
- Ollama · Q2_K Decode 115.28 · Prefill 513.9 ·
- Ollama · Q4_K_S Decode 84.3 · Prefill 357.49 ·
- Strata · IQ2_M Decode 174.12 · Prefill 755.26 ·
- vLLM · Q8_0 (current)Decode 61.2 · Prefill 459 ·
- vLLM · Q5_K_M Decode 89.4 · Prefill 670.5 ·
- llama.cpp · Q8_0 Decode 56.2 · Prefill 421.5 ·
- llama.cpp · Q5_K_M Decode 82 · Prefill 615 ·
Core figures
- Decode (avg)
- 61.2 tok/s
- Prefill (avg)
- 459 tok/s
- TTFT (avg)
- 0.22 s
- VRAM (avg)
- 13.5 GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- Q8_0
- Framework
- vLLM
- Version
- 0.7.3
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 13.5 GB
- OS
- Linux
- Driver
- 570.65
- CUDA
- 12.6
Sources & evidence
1 measured records in total, each traceable to its original source
0.7.3 · Linux · CUDA 12.6 · 4096 ctx
61.2 tok/s
Decode
459 tok/s
Prefill
0.22 s
TTFT
13.5 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算(add-1000-records-batch3)