Back to leaderboard

qwen3.6:35b-a3b-q8_0

OLLAMA GGUF

qwen35moe · 36.0B · Q8_0

Not Rec.

Jul 7, 2026 · Cortex-X925

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
80 vs 66
Hardware Fit
79 vs 87
Quality Score
81 vs 57

Hardware

qwen3.6:35b-a3b-q8_0 granite-3.3-2b-ins…
MachineASUSTeK COMPUTER INC. GX10MacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen3.6:35b-a3b-q8_0 granite-3.3-2b-ins…
Tokens/sec55.518.3
First chunk528 ms541 ms
TTFT30.0 s541 ms
Load time32.6 sN/A
Memory usage41.0 GB4.7 GB
Memory %34%15%

HW Fit Score Breakdown

qwen3.6:35b-a3b-q8_0

Speed
50/50
TTFT
0/20
Memory
29/30

granite-3.3-2b-instruct

Speed
37/50
TTFT
20/20
Memory
30/30

Quality

qwen3.6:35b-a3b-q8_0

Reasoning
18/20
Coding
13/20
Instruction
17/20
Structured
10/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong

granite-3.3-2b-instruct

Reasoning
10/20
Coding
10/20
Instruction
14/20
Structured
14/15
Math
2/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen3.6:35b-a3b-q8_0 details | View granite-3.3-2b-ins… 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