CodeGeeX 4 9B needs ~10.5 GB VRAM. MacBook Pro M1 Pro 32GB has 23.0 GB. With Q4_K_M quantization, expect ~26 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
25.9 tok/s
TTFT
7475 ms
Safe context
131K
Memory
10.5 GB / 23.0 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 25.9 tok/s | 4077 ms | 131K |
| Coding | A | Runs well | 25.9 tok/s | 7475 ms | 131K |
| Agentic Coding | A | Runs well | 25.9 tok/s | 10873 ms | 131K |
| Reasoning | A | Runs well | 25.9 tok/s | 8834 ms | 131K |
| RAG | A | Runs well | 25.9 tok/s | 13591 ms | 131K |
How CodeGeeX 4 9B (9B params) fits at each quantization level on MacBook Pro M1 Pro 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | A73 |
Q3_K_S | 3 | 4.4 GB | Low | A73 |
NVFP4 | 4 | 5.0 GB | Medium | A74 |
Q4_K_M | 4 | 5.5 GB | Medium | A74 |
Q5_K_M | 5 | 6.5 GB | High | A74 |
Q6_K | 6 | 7.4 GB | High | A75 |
Q8_0 | 8 | 9.6 GB | Very High | A77 |
F16Best for your GPU | 16 | 18.5 GB | Maximum | A77 |
Copy-paste commands to run CodeGeeX 4 9B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "THUDM/codegeex4-all-9b" \
--hf-file "codegeex4-all-9b-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | A | 17.7 tok/s | |
| Qwen 3.5 27B | 27B | S | 7.9 tok/s | |
| Qwen 3.6 27B | 27B | S | 6.5 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 18.6 tok/s | |
| Qwen 3.5 35B A3B | 35B | A | 15.4 tok/s |
Yes, MacBook Pro M1 Pro 32GB can run CodeGeeX 4 9B with a A grade (Runs well). Expected decode speed: 25.9 tok/s.
CodeGeeX 4 9B (9B parameters) requires approximately 10.5 GB of memory with Q4_K_M quantization.
The recommended quantization for CodeGeeX 4 9B is Q4_K_M, which balances quality and memory efficiency.
On MacBook Pro M1 Pro 32GB, CodeGeeX 4 9B achieves approximately 25.9 tokens per second decode speed with a time-to-first-token of 7475ms using Q4_K_M quantization.
For coding workloads, CodeGeeX 4 9B on MacBook Pro M1 Pro 32GB receives a A grade with 25.9 tok/s and 131K context.
On MacBook Pro M1 Pro 32GB, CodeGeeX 4 9B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Not always. MacBook Pro M1 Pro 32GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/codegeex-4-9b-on-m1-pro-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: