Back to leaderboard

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

mistral-small:24b

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
59 vs 75
Hardware Fit
69 vs 64
Quality Score
54 vs 80

Hardware

qwen3.5:35b-a3b mistral-small:24b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1420
RAM48 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 26.3.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5:35b-a3b mistral-small:24b
Tokens/sec30.514.3
First chunk333 ms327 ms
TTFT30.0 s327 ms
Load time9.8 s12.0 s
Memory usage25.1 GB18.5 GB
Memory %52%15%

HW Fit Score Breakdown

qwen3.5:35b-a3b

Speed
45/50
TTFT
0/20
Memory
24/30

mistral-small:24b

Speed
14/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5:35b-a3b

Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong

mistral-small:24b

Reasoning
16/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:35b-a3b details | View mistral-small:24b 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