Command R 35B needs ~29.5 GB VRAM. Radeon Pro W7900 48GB has 48.0 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
26.0 tok/s
TTFT
7456 ms
Safe context
131K
Memory
29.5 GB / 48.0 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 | 26.0 tok/s | 4067 ms | 131K |
| Coding | A | Runs well | 26.0 tok/s | 7456 ms | 131K |
| Agentic Coding | A | Runs well | 26.0 tok/s | 10845 ms | 131K |
| Reasoning | A | Runs well | 26.0 tok/s | 8812 ms | 131K |
| RAG | A | Runs well | 26.0 tok/s | 13556 ms | 131K |
Inference speed
Estimated decode speed (tokens/sec) for Command R 35B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~40 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 | 39.6 | Tight |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 30.6 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 30.6 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 28.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 23.6 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 22.4 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 20.5 | Heavy offload |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 19.3 | Tight |
| RTX 4090 24GB | 24 GB | Q4_K_M | 13.1 | Heavy offload |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 12.2 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 12.0 | Heavy offload |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 11.2 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 4.7 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
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 Command R 35B (35B params) fits at each quantization level on Radeon Pro W7900 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | A71 |
Q3_K_S | 3 | 17.2 GB | Low | A72 |
NVFP4 | 4 | 19.6 GB | Medium | A72 |
Q4_K_M | 4 | 21.3 GB | Medium | A73 |
Q5_K_M | 5 | 25.2 GB | High | A74 |
Q6_K | 6 | 28.7 GB | High | A74 |
Q8_0Best for your GPU | 8 | 37.5 GB | Very High | A74 |
F16 | 16 | 71.8 GB | Maximum | F0 |
Copy-paste commands to run Command R 35B on your machine.
Run
ollama run command-rYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen 2.5 VL 72B | 72B | A | 7.2 tok/s | |
| Qwen3-Coder-Next | 80B | A | 18.7 tok/s | |
 Llama 3.3 70B | 70B | A | 7.8 tok/s | |
 Kimi Linear 48B A3B | 48B | A | 17.4 tok/s | |
| Llama 3.1 70B | 70B | B | 7.8 tok/s |
Yes, Radeon Pro W7900 48GB can run Command R 35B with a A grade (Runs well). Expected decode speed: 26.0 tok/s.
Command R 35B (35B parameters) requires approximately 29.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Command R 35B is Q4_K_M, which balances quality and memory efficiency.
On Radeon Pro W7900 48GB, Command R 35B achieves approximately 26.0 tokens per second decode speed with a time-to-first-token of 7456ms using Q4_K_M quantization.
For coding workloads, Command R 35B on Radeon Pro W7900 48GB receives a A grade with 26.0 tok/s and 131K context.
On Radeon Pro W7900 48GB, Command R 35B 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/command-r-35b-on-radeon-pro-w7900-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: