Back to leaderboard

qwen3.6:35b-a3b-q8_0

OLLAMA GGUF

qwen35moe · 36.0B · Q8_0

Not Rec.

Jul 7, 2026 · Cortex-X925

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score
80 vs 69
Hardware Fit
79 vs 50
Quality Score
81 vs 77

Hardware

qwen3.6:35b-a3b-q8_0 mistralai/devstral…
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 mistralai/devstral…
Tokens/sec55.55.7
First chunk528 ms5007 ms
TTFT30.0 s5.0 s
Load time32.6 sN/A
Memory usage41.0 GB13.2 GB
Memory %34%41%

HW Fit Score Breakdown

qwen3.6:35b-a3b-q8_0

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

mistralai/devstral-smal…

Speed
11/50
TTFT
9/20
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

mistralai/devstral-smal…

Reasoning
16/20
Coding
18/20
Instruction
13/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.6:35b-a3b-q8_0 details | View mistralai/devstral… 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