Skip to content
Model Pareto

Qwen3.8 27B NVFP4

NVIDIAOpen weightsNVFP4quantized from Qwen3.8 27Bhuggingface.co ↗
Input
—
Output
—
Speed
~150tok/sest.
Context
262Ktokens

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
1× B200 180GB
NVFP4 weights
Throughput
~5,918 tok/s
many requests batched
Price
$0.14–1.22 /M tok
busy → light use
On your own machine
RTX 5090 32GB (NVFP4, ~80 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • NVFP4 weights (27.8B params) + 25% KV-cache headroom ≈ 20 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~5,918 output tok/s aggregate at batch 169 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~38,242 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

~#6 of 21 (estimated)~79.4%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #5MiniMax-M380.5%
  4. ~#6Qwen3.8 27B NVFP4Estimated79.4%
  5. #6Hy378.0%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#11 of 28 (estimated)~81.9%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #10Ternary Bonsai 27B82.8%
  4. ~#11Qwen3.8 27B NVFP4Estimated81.9%
  5. #11Gemma 4 31B80.0%
No published score — estimated from related benchmarks

Writing & chat

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Qwen3.8 27B NVFP4Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
~#6 of 12 (estimated)~81.3%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #5MiniMax-M3.1-Flash82.5%
  4. ~#6Qwen3.8 27B NVFP4Estimated81.3%
  5. #6Nemotron 3.5 Super VL80.8%
No published score — estimated from related benchmarks
~#4 of 8 (estimated)~87.1%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Qwen3.8 27B NVFP4Estimated87.1%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#20 of 48 (estimated)~18.5%
  1. #1Muse Wonder Full32.6%
  2. #2GPT-6 Astra31.0%
  3. #19MiMo-V2.6-Pro19.2%
  4. ~#20Qwen3.8 27B NVFP4Estimated18.5%
  5. #20Gemini 3.1 Pro17.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~#10 of 25 (estimated)~30.3%
  1. #1Claude Fable 5.273.4%
  2. #2GPT-6 Astra71.0%
  3. #9GPT-5.531.0%
  4. ~#10Qwen3.8 27B NVFP4Estimated30.3%
  5. #10GPT-6 Luna29.1%
No published score — estimated from related benchmarks

Hard reasoning