hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS

OLLAMA GGUF

qwen35 · 27.3B · unknown

Not Rec.

Aug 22, 2026 · Apple M1 Pro

qwen3:1.7b

OLLAMA GGUF

qwen3 · 2.0B · Q4_K_M

Good

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score

31 vs 72

Hardware Fit

37 vs 92

Quality Score

28 vs 63

Hardware

hf.co/unsloth/Qwen… qwen3:1.7b

MachineMacBook ProAZW GTR Pro

CPUApple M1 ProAMD RYZEN AI MAX+ 395

Cores1032

RAM16 GB125 GB

GPUApple M1 ProAMD Radeon 8060S

OSmacOS 26.6.2Ubuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedlow-power

Performance

hf.co/unsloth/Qwen… qwen3:1.7b

Tokens/sec5.4120.7

First chunk5076 ms93 ms

TTFT5.1 s1.5 s

Load time0.3 s2.5 s

Memory usage11.6 GB5.8 GB

Memory %72%5%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed

13/50

TTFT

10/20

Memory

14/30

qwen3:1.7b

Speed

50/50

TTFT

12/20

Memory

30/30

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning

9/20

Coding

2/20

Instruction

1/20

Structured

1/15

Math

9/15

Multilingual

6/10

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

qwen3:1.7b

Reasoning

13/20

Coding

6/20

Instruction

13/20

Structured

14/15

Math

7/15

Multilingual

10/10

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

View hf.co/unsloth/Qwen… details | View qwen3:1.7b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest