CodeGeeX 4 9B needs ~8.9 GB VRAM. RTX 5080 16GB has 16.0 GB. With Q4_K_M quantization, expect ~124 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
124.3 tok/s
TTFT
1557 ms
Safe context
131K
Memory
8.9 GB / 16.0 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 | 124.3 tok/s | 849 ms | 131K |
| Coding | A | Runs well | 124.3 tok/s | 1557 ms | 131K |
| Agentic Coding | A | Runs well | 124.3 tok/s | 2265 ms | 131K |
| Reasoning | A | Runs well | 124.3 tok/s | 1840 ms | 131K |
| RAG | A | Runs well | 124.3 tok/s | 2831 ms | 131K |
How CodeGeeX 4 9B (9B params) fits at each quantization level on RTX 5080 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | A75 |
Q3_K_S | 3 | 4.4 GB | Low | A76 |
NVFP4 | 4 |
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 |
|---|---|---|---|---|
| 14B | S | 78.9 tok/s | ||
| 14.7B | S | 74.8 tok/s |
Yes, RTX 5080 16GB can run CodeGeeX 4 9B with a A grade (Runs well). Expected decode speed: 124.3 tok/s.
CodeGeeX 4 9B (9B parameters) requires approximately 8.9 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 5080 16GB, CodeGeeX 4 9B achieves approximately 124.3 tokens per second decode speed with a time-to-first-token of 1557ms using Q4_K_M quantization.
For coding workloads, CodeGeeX 4 9B on RTX 5080 16GB receives a A grade with 124.3 tok/s and 131K context.
On RTX 5080 16GB, 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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/codegeex-4-9b-on-rtx-5080-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
5.0 GB |
| Medium |
| A77 |
Q4_K_M | 4 | 5.5 GB | Medium | A77 |
Q5_K_M | 5 | 6.5 GB | High | A78 |
Q6_K | 6 | 7.4 GB | High | A79 |
Q8_0Best for your GPU | 8 | 9.6 GB | Very High | A79 |
F16 | 16 | 18.5 GB | Maximum | F0 |
| 21B | A | 71.6 tok/s |
| 14B | S | 78.5 tok/s |
| 22B | A | 27.9 tok/s |