Skip to content
Model Pareto

Qwen3.8 27B NVFP4

NVIDIAOpen weightsNVFP4quantized from Qwen3.8 27Bhuggingface.co ↗
Compare with nearest rivalsCompare with…
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

SWE-bench VerifiedEstimated
~#5 of 14 (estimated)~80.4%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #4MiniMax-M380.5%
  4. ~#5Qwen3.8 27B NVFP4Estimated80.4%
  5. #5Hy378.0%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#28 of 32 (estimated)~55.7%
  1. #1GPT-6.1 Sol75.2%
  2. #2DeepSeek V4.1 Flash74.2%
  3. #27Nex-N2.5-Pro55.8%
  4. ~#28Qwen3.8 27B NVFP4Estimated55.7%
  5. #28Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#9 of 25 (estimated)~79.6%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #8Gemma 4 31B80.0%
  4. ~#9Qwen3.8 27B NVFP4Estimated79.6%
  5. #9gpt-oss-20b77.7%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#11 of 15 (estimated)~44.5
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #10Grok 4.647.0
  4. ~#11Qwen3.8 27B NVFP4Estimated44.5
  5. #11Qwen3.8 Max (0902)43.3
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#2 of 5 (estimated)~90.1%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Qwen3.8 27B NVFP4Estimated90.1%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#16 of 54 (estimated)~1453 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #15GPT-5.6 Terra1456
  4. ~#16Qwen3.8 27B NVFP4Estimated1453
  5. #16DeepSeek V4 Pro (0813)1448
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#16 of 54 (estimated)~1464 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #15GPT-5.6 Terra1466
  4. ~#16Qwen3.8 27B NVFP4Estimated1464
  5. #16DeepSeek V4 Pro (0813)1463
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1956 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #8Grok 4.72007
  4. ~#9Qwen3.8 27B NVFP4Estimated1956
  5. #9Muse Spark 1.31906
No published score — estimated from related benchmarks

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
CharXiv ReasoningEstimated
~#5 of 9 (estimated)~80.9%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5Qwen3.8 27B NVFP4Estimated80.9%
  5. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#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
~#17 of 43 (estimated)~17.1%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #16Grok 4.617.2%
  4. ~#17Qwen3.8 27B NVFP4Estimated17.1%
  5. #17Qwen3.8 27B16.6%
No published score — estimated from related benchmarks
ChartographyEstimated
~#10 of 23 (estimated)~28.2%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #8Qwen3.8 Max (0902)29.1%
  4. ~#10Qwen3.8 27B NVFP4Estimated28.2%
  5. #10Muse Spark 1.327.6%
No published score — estimated from related benchmarks

Hard reasoning

Humanity's Last ExamEstimated
~#44 of 182 (estimated)~29.8%
  1. #1Claude Opus 5.561.4%
  2. #2Claude Fable 5.159.1%
  3. #43Inkling31.9%
  4. ~#44Qwen3.8 27B NVFP4Estimated29.8%
  5. #44A.X-K229.6%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 30 (estimated)~98.9%
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Qwen3.8 27B NVFP4Estimated98.9%
  3. #2Inkling97.1%
No published score — estimated from related benchmarks