Arao AI
Back to search results

Qwen3.5-27B · IQ4_XS

Start a discussion
2x AMD Radeon RX 7900 XTX48GBStrata v0.5.xL2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (IQ4_XS) on 2x AMD Radeon RX 7900 XTX with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

152 tok/s

Decode

Decode speed

1,362 tok/s

Prefill

Prefill speed

1.76 s

TTFT

Time to first token

10.9 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ4_XS Decode 108 · Prefill 939 ·
  2. llama.cpp · Q4_K_M Decode 98 · Prefill 892 ·
  3. llama.cpp · Q5_K_M Decode 80 · Prefill 948 ·
  4. llama.cpp · Q8_0 Decode 66 · Prefill 724 ·
  5. vLLM · IQ4_XS Decode 82 · Prefill 946 ·
  6. vLLM · Q4_K_M Decode 73 · Prefill 855 ·
  7. vLLM · Q5_K_M Decode 75 · Prefill 843 ·
  8. vLLM · Q8_0 Decode 59 · Prefill 489 ·
  9. Ollama · IQ4_XS Decode 94 · Prefill 1095 ·
  10. Ollama · Q4_K_M Decode 87 · Prefill 997 ·
  11. Ollama · Q5_K_M Decode 89 · Prefill 724 ·
  12. Ollama · Q8_0 Decode 59 · Prefill 668 ·
  13. Strata · IQ4_XS (current)Decode 152 · Prefill 1362 ·
  14. Strata · Q4_K_M Decode 139 · Prefill 1188 ·
  15. Strata · Q5_K_M Decode 121 · Prefill 1339 ·
  16. Strata · Q8_0 Decode 87 · Prefill 1027 ·

Core figures

Decode (avg)
152 tok/s
Prefill (avg)
1,362 tok/s
TTFT (avg)
1.76 s
VRAM (avg)
10.9 GB
MTP acceptance rate
—
TTFB
— GB
Power draw
334 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
IQ4_XS
Framework
Strata
Version
v0.5.x
Context length
8192 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
2x AMD Radeon RX 7900 XTX
Nominal VRAM
48 GB
Measured VRAM (avg)
10.9 GB
OS
Linux 6.8.0
Driver
570.86.15
CUDA
12.6
Power draw
334 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-09

    v0.5.x · Linux 6.8.0 · CUDA 12.6 · 8192 ctx

    152 tok/s

    Decode

    1,362 tok/s

    Prefill

    1.76 s

    TTFT

    10.9 GB

    VRAM

    —

    MTP

    334 W

    Power draw

    Auto-generated LLM-sourced record 2026-10-09. Model: Qwen3.5-27B, Hardware: RX 7900 XTX, Framework: 9, Quant: IQ4_XS.