qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Jul 31, 2026 · Intel Xeon® E5-2637 v3

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score

81 vs 69

Hardware Fit

72 vs 50

Quality Score

85 vs 77

Hardware

qwen3.5:35b-a3b-q4… mistralai/devstral…

MachineDell Inc. Precision Tower 7910MacBook Air

CPUIntel Xeon® E5-2637 v3Apple M4

Cores1610

RAM96 GB32 GB

GPUNVIDIA GeForce RTX 5060 TiApple M4

OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… mistralai/devstral…

Tokens/sec24.25.7

First chunk1607 ms5007 ms

TTFT1.6 s5.0 s

Load time66.4 sN/A

Memory usage22.7 GB13.2 GB

Memory %24%41%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed

28/50

TTFT

14/20

Memory

30/30

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning

16/20

Coding

18/20

Instruction

15/20

Structured

15/15

Math

11/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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 qwen3.5:35b-a3b-q4… 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