Back to search results

gemma-4-12B-it · Q5_K_M

Start a discussion
NVIDIA RTX 509032GBllama.cpp b4200L0 Self-reported

This page aggregates 1 real-world runs of gemma-4-12B-it (Q5_K_M) on NVIDIA RTX 5090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

157.1 tok/s

Decode

Decode speed

1,178.3 tok/s

Prefill

Prefill speed

0.08 s

TTFT

Time to first token

9.4 GB

VRAM

VRAM usage

L0 Self-reported

1

Measured runs

1

Independent sources

Other

Source platforms

2026-10-06

Last verified

Performance

  1. llama.cpp · IQ2_XS Decode 262.05 · Prefill 997.54 ·
  2. llama.cpp · Q8_0 Decode 125.52 · Prefill 751.15 ·
  3. Ollama · Q3_K_S Decode 236.13 · Prefill 819.72 ·
  4. Ollama · Q5_K_S Decode 165.12 · Prefill 690.64 ·
  5. vLLM · IQ3_S Decode 261.31 · Prefill 1085.12 ·
  6. vLLM · Q5_K_S Decode 173.67 · Prefill 792.94 ·
  7. Strata · Q3_K_M Decode 340.87 · Prefill 1525.66 ·
  8. llama.cpp · IQ3_S Decode 214.27 · Prefill 831.85 ·
  9. vLLM · IQ1_S Decode 298.32 · Prefill 1152.98 ·
  10. vLLM · IQ2_M Decode 288.51 · Prefill 940.03 ·
  11. Ollama · IQ2_XS Decode 246.6 · Prefill 1083.78 ·
  12. vLLM · Q8_0 Decode 117.2 · Prefill 879 ·
  13. vLLM · Q5_K_M Decode 171.1 · Prefill 1283.3 ·
  14. vLLM · Q4_K_M Decode 208.7 · Prefill 1565.3 ·
  15. llama.cpp · Q5_K_M (current)Decode 157.1 · Prefill 1178.3 ·
  16. llama.cpp · Q4_K_M Decode 191.5 · Prefill 1436.3 ·

Core figures

Decode (avg)
157.1 tok/s
Prefill (avg)
1,178.3 tok/s
TTFT (avg)
0.08 s
VRAM (avg)
9.4 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
Q5_K_M
Framework
llama.cpp
Version
b4200
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 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
9.4 GB
OS
Linux
Driver
570.65
CUDA
12.6

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L0 Self-reportedOtherOriginal link Verified on 2026-10-06

    b4200 · Linux · CUDA 12.6 · 4096 ctx

    157.1 tok/s

    Decode

    1,178.3 tok/s

    Prefill

    0.08 s

    TTFT

    9.4 GB

    VRAM

    —

    MTP

    — W

    Power draw

    L0 理论估算(add-1000-records-batch3)