Mistral Small 24B Instruct 2501 needs ~14.3 GB VRAM. Radeon RX 7800M 12GB has 12.0 GB. With Q2_K quantization, expect ~12 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
7.6 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
4.7 tok/s
TTFT
41434 ms
Safe context
4K
Memory
19.6 GB / 12.0 GB
Offload
40%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 20% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 1.5 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 5.5 tok/s | 19314 ms | 4K |
| Coding | F | Too heavy | 4.7 tok/s | 41434 ms | 4K |
| Agentic Coding | F | Too heavy | 3.5 tok/s | 79973 ms | 4K |
| Reasoning | F | Too heavy | 4.7 tok/s | 48967 ms | 4K |
| RAG | F | Too heavy | 3.5 tok/s | 99966 ms | 4K |
Inference speed
Estimated decode speed (tokens/sec) for Mistral Small 24B Instruct 2501 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~82 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 | 82.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 52.3 | Tight |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 47.2 | Tight |
| RTX 3090 24GB | 24 GB | Q4_K_M | 44.8 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 38.0 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 34.2 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 34.2 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 31.7 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 30.1 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 21.5 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 19.1 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 16.4 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 15.0 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 6.7 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 4.2 | 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 Mistral Small 24B Instruct 2501 (24B params) fits at each quantization level on Radeon RX 7800M 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | F0 |
Q3_K_S | 3 | 11.8 GB | Low | F0 |
NVFP4 | 4 | 13.4 GB | Medium | F0 |
Q4_K_M | 4 | 14.6 GB | Medium | F0 |
Q5_K_M | 5 | 17.3 GB | High | F0 |
Q6_K | 6 | 19.7 GB | High | F0 |
Q8_0 | 8 | 25.7 GB | Very High | F0 |
F16 | 16 | 49.2 GB | Maximum | F0 |
Copy-paste commands to run Mistral Small 24B Instruct 2501 on your machine.
Run
lms load hf-maziyarpanahi--mistral-small-24b-instruct-2501-gguf && lms server startUpgrade-Optionen
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $899 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $999 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $1,899 MSRP
Yes, Radeon RX 7800M 12GB can run Mistral Small 24B Instruct 2501 at Q2_K quantization (Very compromised (needs ~1.5 GB host RAM)). The recommended Q4_K_M requires 19.6 GB which exceeds available memory, but at Q2_K it needs only 14.3 GB. Expected decode speed: 12.1 tok/s.
Mistral Small 24B Instruct 2501 (24B parameters) requires approximately 19.6 GB at Q4_K_M quantization. On Radeon RX 7800M 12GB, it fits at Q2_K using 14.3 GB.
The recommended quantization is Q4_K_M, but on Radeon RX 7800M 12GB the best fitting quantization is Q2_K, which uses 14.3 GB.
On Radeon RX 7800M 12GB, Mistral Small 24B Instruct 2501 achieves approximately 12.1 tokens per second decode speed with a time-to-first-token of 16066ms using Q2_K quantization.
For coding workloads, Mistral Small 24B Instruct 2501 on Radeon RX 7800M 12GB receives a F grade with 4.7 tok/s and 4K context.
On Radeon RX 7800M 12GB, Mistral Small 24B Instruct 2501 can safely use up to 4K tokens of context at Q2_K quantization. The model's official context limit is —, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-maziyarpanahi--mistral-small-24b-instruct-2501-gguf-on-rx-7800m-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: