Back to leaderboard

internlm2_5-1_8b-chat

LM-STUDIO GGUF

internlm2 · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

qwen2.5-coder-3b-instruct-mlx

LM-STUDIO MLX

qwen2 · 3B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score
55 vs 73
Hardware Fit
60 vs 100
Quality Score
53 vs 61

Hardware

internlm2_5-1_8b-c… qwen2.5-coder-3b-i…
MachineLENOVO 20BUS00700MacBook Air
CPUIntel Core™ i5-5300UApple M4
Cores410
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500Apple M4
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

internlm2_5-1_8b-c… qwen2.5-coder-3b-i…
Tokens/sec6.652.3
First chunk3037 ms285 ms
TTFT3.0 s285 ms
Load timeN/AN/A
Memory usage1.1 GB1.6 GB
Memory %7%5%

HW Fit Score Breakdown

internlm2_5-1_8b-chat

Speed
23/50
TTFT
16/20
Memory
21/30

qwen2.5-coder-3b-instru…

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

Quality

internlm2_5-1_8b-chat

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

qwen2.5-coder-3b-instru…

Reasoning
7/20
Coding
14/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View internlm2_5-1_8b-c… details | View qwen2.5-coder-3b-i… 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