Back to leaderboard

deepseek-coder-1.3b-instruct

LM-STUDIO GGUF

llama · 1.3B · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
30 vs 88
Hardware Fit
66 vs 85
Quality Score
14 vs 89

Hardware

deepseek-coder-1.3… huihui-qwen3.6-35b…
MachineLENOVO 20BUS00700Gigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-5300UAMD Ryzen 5 5600X 6-Core Processor
Cores412
RAM16 GB47 GB
GPUIntel(R) HD Graphics 5500AD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 10 Professionnel 10.0.19045cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

deepseek-coder-1.3… huihui-qwen3.6-35b…
Tokens/sec7.137.7
First chunk3448 ms18 ms
TTFT3.4 s2.9 s
Load timeN/AN/A
Memory usage1.3 GB26.1 GB
Memory %9%56%

HW Fit Score Breakdown

deepseek-coder-1.3b-ins…

Speed
24/50
TTFT
15/20
Memory
27/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

Quality

deepseek-coder-1.3b-ins…

Reasoning
0/20
Coding
3/20
Instruction
3/20
Structured
6/15
Math
0/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Poor Multilingual: Poor

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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