Compare models on your machine
Not generic leaderboards: every model is rated for your hardware, your tool and your workload — so you can see which one will actually feel better to use.
MacBook Pro M4 Pro 48 GB · Agentic coding / medium repository
- Qwen3.6 35B-A3B5-bit · LM StudioComfortableSpeed 50–70 tok/sUses 25 GBFree 12 GB
- Qwen3.5 35B-A3B5-bit · LM StudioComfortableSpeed 50–70 tok/sUses 25 GBFree 12 GB
- GLM-4.7-Flash (30B-A3B)6-bit · LM StudioComfortableSpeed 35–50 tok/sUses 26 GBFree 10 GB
- Gemma 4 E4B6-bit · LM StudioBorderlineSpeed 25–30 tok/sUses 8.2 GBFree 28 GB
| Model | Confidence | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B-A3B5-bit · LM Studio | Comfortable | 25 GB | 12 GB | Excellent50–70 tok/s | Comfortable | 128K | Strong | Strong | Medium confidence |
| Qwen3.5 35B-A3B5-bit · LM Studio | Comfortable | 25 GB | 12 GB | Excellent50–70 tok/s | Comfortable | 128K | Good | Good | Medium confidence |
| GLM-4.7-Flash (30B-A3B)6-bit · LM Studio | Comfortable | 26 GB | 10 GB | Comfortable35–50 tok/s | Comfortable | 128K | Strong | Strong | Medium confidence |
| Gemma 4 E4B6-bit · LM Studio | Borderline | 8.2 GB | 28 GB | Adequate25–30 tok/s | Comfortable | 128K | Weak | Weak | Medium confidence |
Gemma 4 E4B
6-bit · LM Studio
It runs, but we don't recommend it for agentic coding: weak coding capability for agentic coding. Tool calling is only basic; OpenCode may occasionally fail to call tools correctly; generation (25–30 tok/s) is adequate but not ideal for agentic coding.
≈28 GB headroom
25–30 tok/s
≈30 s first prompt
32K context
Official
Poorly suited
Qwen3.6 35B-A3B
5-bit · LM Studio
Yes — this should be comfortable for agentic coding.
≈12 GB headroom
50–70 tok/s
≈20 s first prompt
32K context
Official
Suited
Qwen3.5 35B-A3B
5-bit · LM Studio
Yes — this should be comfortable for agentic coding.
≈12 GB headroom
50–70 tok/s
≈20 s first prompt
32K context
Official
Suited
GLM-4.7-Flash (30B-A3B)
6-bit · LM Studio
Yes — this should be comfortable for agentic coding.
≈10 GB headroom
35–50 tok/s
≈25 s first prompt
32K context
Official
Suited