Qwen3.8-27B · IQ1_S
This page aggregates 1 real-world runs of Qwen3.8-27B (IQ1_S) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
68.56 tok/s
Decode
Decode speed
341.84 tok/s
Prefill
Prefill speed
1.19 s
TTFT
Time to first token
22.8 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- vLLM · IQ1_S (current)Decode 68.56 · Prefill 341.84 ·
- llama.cpp · IQ4_XS Decode 51.3 · Prefill 384.8 ·
- llama.cpp · Q5_K_S Decode 41.1 · Prefill 308.3 ·
- llama.cpp · IQ3_XXS Decode 78.8 · Prefill 591 ·
- llama.cpp · Q6_K Decode 31.6 · Prefill 237 ·
- llama.cpp · Q4_K_M Decode 124.1 · Prefill 156 ·
- llama.cpp · IQ3_S Decode 26.73 · Prefill 487.5 ·
Core figures
- Decode (avg)
- 68.56 tok/s
- Prefill (avg)
- 341.84 tok/s
- TTFT (avg)
- 1.19 s
- VRAM (avg)
- 22.8 GB
- MTP acceptance rate
- —
- TTFB
- 0.55 GB
- Power draw
- 260.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- IQ1_S
- Framework
- vLLM
- Version
- v0.51
- Context length
- 4096 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
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 6.11
- CUDA
- 12.8
- Power draw
- 260.2 W
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · Windows 11 23H2 · CUDA 12.8 · 4096 ctx
68.56 tok/s
Decode
341.84 tok/s
Prefill
1.19 s
TTFT
22.8 GB
VRAM
—
MTP
260.2 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=11 running model_id=5 at IQ1_S