Leaderboard / Alibaba (Qwen)

Qwen3.8 27B

Name: Qwen3.8 27B
Price: 0.13 USD
Author: Alibaba (Qwen)

Alibaba (Qwen) · Qwen3.8 · released 2026-08-14 · data checked 2026-11-01

Qwen3.8 27B is a 27B-parameter dense model from Alibaba (Qwen) (China), released 2026-08-14 under the Apache-2.0 license. It scores 77.0 on the Small LM Index, #2 of 34 medium models. It needs about 17.9 GB of memory at 4-bit with an 8K-token context and costs $0.13 per million tokens through the cheapest API provider.

Small LM Index

77.0

#2 of 34 scored medium models

Likely 75.9–78.8 · from 3 of 6 core benchmarks

Parameters

27B

Dense

Price per 1M tokens

$0.13

$0.009 in / $0.49 out · blended 3:1

Context window

262K

tokens

Benchmarks

Each bar shows this model's score. The tick marks the best medium model on that benchmark. Sources: 5 reported by Alibaba (Qwen). How we label sources.

GPQA Diamond Lab-reported Knowledge89.2

Class best: Nanbeige4.3 33B 89.5

Humanity's Last Exam Lab-reported Reasoning30.8

LiveCodeBench Lab-reported Coding · LiveCodeBench v690.3

Terminal-Bench Lab-reported Agentic · Terminal-Bench 2.1 (Terminus)73.0

Class best: Nanbeige4.3 33B 80.9

IFBench Lab-reported Instruction following79.5

Class best: Sage-A1.5 81.6

Not reported: estimated

What the index model expects from this model's other scores. Not a measurement.

MMLU-Pro≈ 86

AIME≈ 96

SWE-bench Verified≈ 77

Specifications

Lab: Alibaba (Qwen) (CN · China)
Architecture: Dense transformer
Total parameters: 27B
Active parameters: All (dense)
Size class: Medium
Context window: 262K tokens
Input modalities: text, image, video
Reasoning: Hybrid (thinking on/off)
License: Apache-2.0
Openness: Open weights
Memory to run: ~17.9 GB at 4-bit, 8K context (more sizes)
Hugging Face: 8M downloads (30 days) · 19K likes
API providers: 23 on OpenRouter
API price: $0.009 in / $0.49 out per 1M (OpenRouter, 2026-11-03)

Weights on Hugging Face ↗Try on OpenRouter ↗

Compare with

Qwen3.8 27B vs Qwen3.6 27B (27B, index 74.0)
Qwen3.8 27B vs Qwen3.5 27B (27B, index 70.6)
Qwen3.8 27B vs Ternary Bonsai 2 27B (27.4B, index 74.6)
Qwen3.8 27B vs Gemma 3 27B (27.4B, index 32.7)
Qwen3.8 27B vs DiffusionGemma 26B-A4B (25.8B, index 52.6)

Ranked in

Sources

https://huggingface.co/Qwen/Qwen3.8-27B

Something wrong here? Report it.

Run it locally

Uses ggml-org/Qwen3.8-27B-GGUF (Q4_K_M). Swap the tag for another size: BF16, Q4_0, Q4_K_M, Q8_0.

Ollama

ollama run hf.co/ggml-org/Qwen3.8-27B-GGUF:Q4_K_M

llama.cpp

llama-server -hf ggml-org/Qwen3.8-27B-GGUF:Q4_K_M

Then open http://localhost:8080 for a chat window.

MLX (Mac)

pip install -U mlx-lm
mlx_lm.chat --model mlx-community/Qwen3.8-27B-4bit

Text only; for images use mlx-vlm.

vLLM (GPU server)

vllm serve Qwen/Qwen3.8-27B

Full-precision weights, for a server GPU.

Open in LM Studio

Memory needed: weights, context cache and runtime buffers.

Quantization	4K context	32K context	256K context
16-bit F16	55 GB	57 GB	72 GB
8-bit Q8_0	30 GB	32 GB	47 GB
4-bit Q4_K_M	18 GB	20 GB	35 GB

Check it against your GPU, Mac or phone →