Qwen2.5 Coder 32B Instruct
Alibaba Qwen
The strongest open code model that still fits one 24 GB card. The reason a lot of people buy a 4090.
Good fit
- Weights
- 61 GB
- KV cache
- 2.0 GB
- Overhead
- 1.0 GB
- 64 GB of 96 GB usable unified memory.
- Chosen as the best quality that still fits a 32,768-token context (70 GB at that length).
- Best open-weight coding quality at this size
- Apache 2.0
- Strong multi-file reasoning
- Needs Q4_K_M on 24 GB
- Too slow for keystroke-latency completion on most cards
qwen2.5-coder:32bRunning Qwen2.5 Coder 32B Instruct on MacBook Pro M4 Max (128 GB)
| Quantization | Quality | Weights | KV cache | Total | ~tok/s | Fit |
|---|---|---|---|---|---|---|
| F16Pick | lossless | 61 GB | 2.0 GB | 64 GB | 6 | Good fit |
| Q8_0 | near-lossless | 32 GB | 2.0 GB | 36 GB | 12 | Excellent fit |
| Q6_K | near-lossless | 25 GB | 2.0 GB | 28 GB | 16 | Excellent fit |
| Q5_K_M | high | 22 GB | 2.0 GB | 25 GB | 18 | Excellent fit |
| Q4_K_M | balanced | 18 GB | 2.0 GB | 21 GB | 21 | Excellent fit |
| Q3_K_M | degraded | 15 GB | 2.0 GB | 18 GB | 26 | Excellent fit |
KV cache is sized at 8,192 tokens. Longer contexts cost proportionally more — the recommendation above reserves room for a working context.
You can fine-tune this here
- Base weights
- 17 GB
- Optimizer
- 1.0 GB
- Activations
- 1.9 GB
- Peak
- 22 GB
- 22 GB peak against 96 GB usable — room to raise batch size or sequence length.
- Apple Silicon trains through MLX rather than CUDA kernels.
- Base weights
- 61 GB
- Optimizer
- 1.0 GB
- Activations
- 1.9 GB
- Peak
- 66 GB
- 66 GB peak against 96 GB usable — room to raise batch size or sequence length.
- Apple Silicon trains through MLX rather than CUDA kernels.
Where this model runs
VRAM 32 GB · Q4_K_M · 21 GB
VRAM 24 GB · Q4_K_M · 21 GB
VRAM 16 GB · Q4_K_M · 21 GB
VRAM 16 GB · Q4_K_M · 21 GB
VRAM 24 GB · Q4_K_M · 21 GB
VRAM 12 GB · Q4_K_M · 21 GB
VRAM 12 GB · Q4_K_M · 21 GB
VRAM 16 GB · Q4_K_M · 21 GB
VRAM 48 GB · Q6_K · 28 GB
VRAM 80 GB · Q8_0 · 36 GB
Unified 128 GB · F16 · 64 GB
Unified 48 GB · Q4_K_M · 21 GB
Unified 24 GB · Q3_K_M · 18 GB
Unified 192 GB · F16 · 64 GB
Unified 16 GB · Q4_K_M · 21 GB
VRAM 24 GB · Q4_K_M · 21 GB
VRAM 16 GB · Q4_K_M · 21 GB
VRAM 0 MB
VRAM 0 MB
92.7%
Qwen2.5-Coder model card
Reported by the model's author. ModelLM has not run these benchmarks and does not treat them as verified.
Qwen2.5 7B Instruct
7.6B · Apache 2.0
The default starting point for local work on 8–12 GB cards. Strong instruction following and reliable tool-call formatting for its size.
Qwen2.5 14B Instruct
14.8B · Apache 2.0
The sweet spot for 24 GB cards. Meaningfully stronger reasoning than 7B while still fine-tunable locally with QLoRA.
Qwen2.5 32B Instruct
32.8B · Apache 2.0
Approaches 70B quality at half the memory. Runs on a single 24 GB card at Q4_K_M with a modest context window.
Qwen2.5 72B Instruct
72.7B · Qwen License
Frontier-adjacent open weights. Needs a workstation, a multi-GPU rig or a large unified-memory Mac.
Catalogue figures come from each model’s published card. ModelLM has not independently measured them.