hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_S

qwen35 · 27.3B · unknown

MacBook Pro (Apple M1 Pro)

16 GB · macOS 26.6.2

Tested on August 25, 2026 · Submitted by AAA

Top 90% Compare

Global Score

46 /100

Marginal

Hardware Fit

50/100

Quality

44/100

Get this model

🦙

Ollama

ollama pull hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_S

View on Ollama Library

ollama.com/library/hf.co/unsloth/Qwen3.8-27B-GGUF

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Pro
CPU: Apple M1 Pro
Cores: 10 total (8 perf + 2 eff)
Frequency: 2.4 GHz
RAM: 16 GB LPDDR5
GPU: Apple M1 Pro
OS: macOS 26.6.2
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 6.0
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±399997.6
First chunk latency Delay before the first streamed chunk arrives from runtime: 2.4 s
Time to first token How fast the model starts responding — lower is better: 2.2 s
Load time Time to load the model into memory before inference: 6.8 s
Memory usage RAM consumed during inference — percentage of total system memory: 10.6 GB (66%)
Total tokens Total number of tokens generated across all benchmark prompts: 726

Score breakdown

Speed

15/50

Time to first token

18/20

Memory

17/30

Quality

Reasoning

8/20

Coding

5/20

Instruction following

10/20

Structured output

11/15

Math

3/15

Multilingual

7/10

Category levels

Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.32.15
Model format: GGUF
Hardware profile: ENTRY
Result hash: 5475f51f21418b6c0ce572c4000d3763a6373704d70f3946f9bc8326de72ce09

Interpretation

Hardware fit: 50/100. Overall suitability: MARGINAL (Global 46/100). Category profile: Reasoning: Weak, Coding: Weak, Instruction Following: Adequate, Structured Output: Adequate, Math: Poor, Multilingual: Adequate.

Warnings

Token speed is unstable (stddev 399997.6 tok/s, mean 6.0 tok/s) — may indicate thermal throttling or memory pressure.
Significant swap activity during benchmark (+1.7 GB). Model may exceed available RAM — results are severely degraded.

Bench Environment

Power: AC Swap delta: +1.7 GB CPU load: avg 36% (peak 47%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest