Mistral Small 4 119B needs ~88.5 GB VRAM. NVIDIA H20 96GB has 96.0 GB. With Q4_K_M quantization, expect ~141 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
Tight fit
Decode
141.2 tok/s
TTFT
1371 ms
Safe context
38K
Memory
88.5 GB / 96.0 GB
This setup is broadly balanced for this model.
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Tight fit | 141.2 tok/s | 748 ms | 38K |
| Coding | S | Tight fit | 141.2 tok/s | 1371 ms | 38K |
| Agentic Coding | S | Runs with offload | 141.2 tok/s | 1994 ms | 38K |
| Reasoning | S | Tight fit | 141.2 tok/s | 1620 ms | 38K |
| RAG | S | Runs with offload | 141.2 tok/s | 2492 ms | 38K |
How Mistral Small 4 119B (119B params) fits at each quantization level on NVIDIA H20 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 46.4 GB | Low | S88 |
Q3_K_S | 3 | 58.3 GB | Low | S88 |
NVFP4 | 4 |
Copy-paste commands to run Mistral Small 4 119B on your machine.
Run
lms load Mistral-Small-4-119B-2603 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 47 tok/s | ||
| 122B | S |
Yes, NVIDIA H20 96GB can run Mistral Small 4 119B with a S grade (Tight fit). Expected decode speed: 141.2 tok/s.
Mistral Small 4 119B (119B parameters) requires approximately 88.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Mistral Small 4 119B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA H20 96GB, Mistral Small 4 119B achieves approximately 141.2 tokens per second decode speed with a time-to-first-token of 1371ms using Q4_K_M quantization.
For coding workloads, Mistral Small 4 119B on NVIDIA H20 96GB receives a S grade with 141.2 tok/s and 38K context.
On NVIDIA H20 96GB, Mistral Small 4 119B can safely use up to 38K tokens of context. The model's official context limit is 256K, 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/mistral-small-4-119b-on-h20-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
66.6 GB |
| Medium |
| S88 |
Q4_K_MBest for your GPU | 4 | 72.6 GB | Medium | S88 |
Q5_K_M | 5 | 85.7 GB | High | F0 |
Q6_K | 6 | 97.6 GB | High | F0 |
Q8_0 | 8 | 127.3 GB | Very High | F0 |
F16 | 16 | 244.0 GB | Maximum | F0 |
| 130.3 tok/s |
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.