CodeGeeX 4 9B needs ~8.5 GB VRAM. RTX 4070 12GB has 12.0 GB. With Q4_K_M quantization, expect ~75 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
75.3 tok/s
TTFT
2571 ms
Safe context
108K
Memory
8.5 GB / 12.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 75.3 tok/s | 1402 ms | 108K |
| Coding | A | Runs well | 75.3 tok/s | 2571 ms | 108K |
| Agentic Coding | A | Runs well | 75.3 tok/s | 3739 ms | 108K |
| Reasoning | A | Runs well | 75.3 tok/s | 3038 ms | 108K |
| RAG | A | Runs well | 75.3 tok/s | 4674 ms | 108K |
Inference speed
Estimated decode speed (tokens/sec) for CodeGeeX 4 9B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~126 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 126.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 126.0 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 126.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 126.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 121.7 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 111.0 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 92.4 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 87.7 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 75.3 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 74.7 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 74.7 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 47.8 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 47.3 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 43.8 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 38.5 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 36.4 | Offloads |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How CodeGeeX 4 9B (9B params) fits at each quantization level on RTX 4070 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | A78 |
Q3_K_S | 3 | 4.4 GB | Low | A79 |
NVFP4 | 4 | 5.0 GB | Medium | A80 |
Q4_K_M | 4 | 5.5 GB | Medium | A80 |
Q5_K_M | 5 | 6.5 GB | High | A80 |
Q6_KBest for your GPU | 6 | 7.4 GB | High | A80 |
Q8_0 | 8 | 9.6 GB | Very High | F0 |
F16 | 16 | 18.5 GB | Maximum | F0 |
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 |
|---|---|---|---|---|
 Qwen 3 14B | 14B | A | 28.5 tok/s | |
 Ministral 3 14B | 14B | A | 28.4 tok/s | |
 Phi-4 14B | 14B | A | 25.8 tok/s | |
| Qwen 2.5 14B | 14B | A | 26.4 tok/s |
Yes, RTX 4070 12GB can run CodeGeeX 4 9B with a A grade (Runs well). Expected decode speed: 75.3 tok/s.
CodeGeeX 4 9B (9B parameters) requires approximately 8.5 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 RTX 4070 12GB, CodeGeeX 4 9B achieves approximately 75.3 tokens per second decode speed with a time-to-first-token of 2571ms using Q4_K_M quantization.
For coding workloads, CodeGeeX 4 9B on RTX 4070 12GB receives a A grade with 75.3 tok/s and 108K context.
On RTX 4070 12GB, CodeGeeX 4 9B can safely use up to 108K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/codegeex-4-9b-on-rtx-4070-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: