Leanstral 119B A6B needs ~102.6 GB VRAM. H100 NVL 188GB has 188.0 GB. With Q4_K_M quantization, expect ~193 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
138.6 tok/s
TTFT
1397 ms
Safe context
172K
Memory
102.6 GB / 188.0 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 | S | Runs well | 192.5 tok/s | 549 ms | 172K |
| Coding | S | Runs well | 192.5 tok/s | 1006 ms | 172K |
| Agentic Coding | S | Runs well | 192.5 tok/s | 1463 ms | 172K |
| Reasoning | S | Runs well | 192.5 tok/s | 1189 ms | 172K |
| RAG | S | Runs well | 192.5 tok/s | 1829 ms | 172K |
How Leanstral 119B A6B (119B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 46.4 GB | Low | A77 |
Q3_K_S | 3 | 58.3 GB | Low | A78 |
NVFP4 | 4 |
Copy-paste commands to run Leanstral 119B A6B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "mistralai/Leanstral-2603" \
--hf-file "Leanstral-2603-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 73.3 tok/s | ||
| 122B | S |
Yes, H100 NVL 188GB can run Leanstral 119B A6B with a S grade (Runs well). Expected decode speed: 192.5 tok/s.
Leanstral 119B A6B (119B parameters) requires approximately 102.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Leanstral 119B A6B is Q4_K_M, which balances quality and memory efficiency.
On H100 NVL 188GB, Leanstral 119B A6B achieves approximately 192.5 tokens per second decode speed with a time-to-first-token of 1006ms using Q4_K_M quantization.
For coding workloads, Leanstral 119B A6B on H100 NVL 188GB receives a S grade with 192.5 tok/s and 172K context.
On H100 NVL 188GB, Leanstral 119B A6B can safely use up to 172K 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/leanstral-119b-a6b-on-h100-nvl-188gb" 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 |
| A79 |
Q4_K_M | 4 | 72.6 GB | Medium | A80 |
Q5_K_M | 5 | 85.7 GB | High | A82 |
Q6_K | 6 | 97.6 GB | High | A83 |
Q8_0Best for your GPU | 8 | 127.3 GB | Very High | A84 |
F16 | 16 | 244.0 GB | Maximum | F0 |
| 139 tok/s |
| 124B | S | 72.7 tok/s |
| 235B | S | 70.4 tok/s |
| MiniMax M2.7 | 230B | S | 80 tok/s |