MacBook Pro M4 Max 48GBGünstige Wahl
48 GB Unified (+16)546 GB/s (+34)
B
This setup is broadly balanced for this model.33 tok/s Dekodierung
ca. $2,499 MSRP
Can Cerebras-GPT 13B run on Radeon Pro W6800 32GB?
YES — Runs Great
B70Good
Estimated from fit model
Cerebras-GPT 13B needs ~23.5 GB VRAM. Radeon Pro W6800 32GB has 32.0 GB. With Q5_K_M quantization, expect ~31 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: BasicBottleneck: Balanced
Operating mode
Choose the run profile you care about
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
Q5_K_M (High quality) — 23.5 GB, 31.2 tok/s, Runs well
23.5 GB required32.0 GB available
73% VRAM used
Fit status
Runs well
Decode
31.2 tok/s
TTFT
6196 ms
Safe context
30K
Memory
23.5 GB / 32.0 GB
Memory breakdown
Weights9.4 GB
KV Cache9.8 GB
Runtime1.2 GB
Headroom3.2 GB
See how fast it feels
See how fast it feelsCerebras-GPT 13B on Radeon Pro W6800 32GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.
Given information:
- Speed = 60 mph (miles per hour)
- Time = 2.5 hours
Formula: Distance = Speed x Time
Calculation:
Distance = 60 mph x 2.5 h
= 150 miles
The train travels 150 miles.
Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.
Breakdown:
- First half: 1.25 hours at 60 mph = 75 miles
- Stop: 20 minutes (no distance)
- Second half: 1.25 hours at 60 mph = 75 miles
Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph
The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 31.2 tok/s decode · 6.2s TTFT (warm) · 78 tok/s prefill
What limits this setup
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.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 31.2 tok/s | 3380 ms | 30K |
| Coding | B | Runs well | 31.2 tok/s | 6196 ms | 30K |
| Agentic Coding | B | Runs with offload (needs ~0.4 GB host RAM) | 21.6 tok/s | 13060 ms | 30K |
| Reasoning | B | Runs well | 31.2 tok/s | 7323 ms | 30K |
| RAG | B | Runs with offload (needs ~0.4 GB host RAM) | 21.6 tok/s | 16325 ms | 30K |
Inference speed
Cerebras-GPT 13B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Cerebras-GPT 13B at Q5_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~131 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 | Q5_K_M | 130.8 | Fits |
| RTX 4090 24GB | 24 GB | Q5_K_M | 83.5 | Tight |
RX 7900 XTX 24GB | 24 GB | Q5_K_M | 75.3 | Tight |
| RTX 3090 24GB | 24 GB | Q5_K_M | 71.4 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q5_K_M | 60.7 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q5_K_M | 50.6 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q5_K_M | 47.9 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q5_K_M | 33.0 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q5_K_M | 33.0 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q5_K_M | 26.2 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q5_K_M | 25.7 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q5_K_M | 24.0 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q5_K_M | 20.2 | Fits |
| RTX 4070 12GB | 12 GB | Q5_K_M | 9.0 | Too big |
| RTX 3060 12GB | 12 GB | Q5_K_M | 5.7 | Too big |
| RTX 4060 8GB | 8 GB | Q5_K_M | 3.2 | Too big |
Estimates for single-stream decoding at Q5_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.
Quantization options
How Cerebras-GPT 13B (13B params) fits at each quantization level on Radeon Pro W6800 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | B60 |
Q3_K_S | 3 | 6.4 GB | Low | B60 |
NVFP4 | 4 | 7.3 GB | Medium | B61 |
Q4_K_M | 4 | 7.9 GB | Medium | B61 |
Q5_K_M | 5 | 9.4 GB | High | B62 |
Q6_K | 6 | 10.7 GB | High | B62 |
Q8_0 | 8 | 13.9 GB | Very High | B64 |
F16Best for your GPU | 16 | 26.7 GB | Maximum | B65 |
Get started
Copy-paste commands to run Cerebras-GPT 13B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "cerebras/Cerebras-GPT-13B" \
--hf-file "Cerebras-GPT-13B-Q5_K_M.gguf" \
-c 4096 -ngl 99Upgrade-Optionen
Hardware, die Cerebras-GPT 13B gut ausführt
Frequently asked questions
Can Radeon Pro W6800 32GB run Cerebras-GPT 13B?
Yes, Radeon Pro W6800 32GB can run Cerebras-GPT 13B with a B grade (Runs well). Expected decode speed: 31.2 tok/s.
How much VRAM does Cerebras-GPT 13B need?
Cerebras-GPT 13B (13B parameters) requires approximately 23.5 GB of memory with Q5_K_M quantization.
What is the best quantization for Cerebras-GPT 13B?
The recommended quantization for Cerebras-GPT 13B is Q5_K_M, which balances quality and memory efficiency.
What speed will Cerebras-GPT 13B run at on Radeon Pro W6800 32GB?
On Radeon Pro W6800 32GB, Cerebras-GPT 13B achieves approximately 31.2 tokens per second decode speed with a time-to-first-token of 6196ms using Q5_K_M quantization.
Can Radeon Pro W6800 32GB run Cerebras-GPT 13B for coding?
For coding workloads, Cerebras-GPT 13B on Radeon Pro W6800 32GB receives a B grade with 31.2 tok/s and 30K context.
What context window can Cerebras-GPT 13B use on Radeon Pro W6800 32GB?
On Radeon Pro W6800 32GB, Cerebras-GPT 13B can safely use up to 30K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/cerebras-gpt-13b-on-radeon-pro-w6800-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: