Back to leaderboard

deepseek-coder:6.7b

OLLAMA GGUF

llama · 7B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

qwen3.5-35b-a3b-mtp

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
57 vs 77
Hardware Fit
98 vs 51
Quality Score
39 vs 88

Hardware

deepseek-coder:6.7b qwen3.5-35b-a3b-mtp
MachineMacBook AirDocker Container
CPUApple M4Intel Gen Intel® Core™ i9-11900H
Cores1016
RAM32 GB15 GB
GPUApple M4TigerLake-H GT1 [UHD Graphics]
OSmacOS 26.3Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

deepseek-coder:6.7b qwen3.5-35b-a3b-mtp
Tokens/sec24.17.8
First chunkN/A30 ms
TTFT251 ms5.6 s
Load time0.9 s32.5 s
Memory usage12.6 GB0.0 GB
Memory %39%0%

HW Fit Score Breakdown

deepseek-coder:6.7b

Speed
38/50
TTFT
30/20
Memory
30/30

qwen3.5-35b-a3b-mtp

Speed
14/50
TTFT
7/20
Memory
30/30

Quality

deepseek-coder:6.7b

Reasoning
4/20
Coding
14/20
Instruction
9/20
Structured
6/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak

qwen3.5-35b-a3b-mtp

Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View deepseek-coder:6.7b details | View qwen3.5-35b-a3b-mtp 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