Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 19, 2026 · Apple M4 Max

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

Global Score
83 vs 80
Hardware Fit
68 vs 100
Quality Score
90 vs 71

Hardware

qwen/qwen3.8-27b gemma-3-4b-it-q4-k-m
MachineMacBook ProMac Pro
CPUApple M4 MaxIntel Core™ i5-10400
Cores1612
RAM128 GB32 GB
GPUApple M4 MaxAMD Radeon RX 6700 XT
OSmacOS 26.5.2macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b gemma-3-4b-it-q4-k-m
Tokens/sec27.675.0
First chunk10 ms136 ms
TTFT4.6 s136 ms
Load timeN/A0.0 s
Memory usage21.0 GB0.8 GB
Memory %16%3%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
32/50
TTFT
6/20
Memory
30/30

gemma-3-4b-it-q4-k-m

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

qwen/qwen3.8-27b

Reasoning
19/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma-3-4b-it-q4-k-m

Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen/qwen3.8-27b details | View gemma-3-4b-it-q4-k-m 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