Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Aug 22, 2026 · Intel Xeon® E5-2637 v3

qwen3.8-27b-claude-opus-reasoning-distilled

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Aug 20, 2026 · Apple M4 Max

Global Score
90 vs 80
Hardware Fit
98 vs 63
Quality Score
86 vs 87

Hardware

qwen3.5:35b-a3b-q4… qwen3.8-27b-claude…
MachineDell Inc. Precision Tower 7910MacBook Pro
CPUIntel Xeon® E5-2637 v3Apple M4 Max
Cores1616
RAM96 GB128 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M4 Max
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… qwen3.8-27b-claude…
Tokens/sec48.424.0
First chunk1085 ms20 ms
TTFT1.1 s4.5 s
Load time22.2 sN/A
Memory usage22.9 GB15.7 GB
Memory %24%12%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
50/50
TTFT
18/20
Memory
30/30

qwen3.8-27b-claude-opus…

Speed
27/50
TTFT
6/20
Memory
30/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.8-27b-claude-opus…

Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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