Mistral AI, France · Released July 2, 2026
Leanstral 1.5 119B-A6B has 119.4B parameters (6.5B active per token). In BF16 its weights alone take 222 GiB; quantized to 4-bit, about 67.0 GiB. Each 32K-token request adds 0.70 GiB of KV cache. Cheapest way to run it today: 5 × RTX A4000 (16 GB) at $0.360 per hour. It calls tools and lets you set its reasoning effort.
Size your own setup in the calculator →vLLM needs one extra install first: uv pip install -U vllm --torch-backend=auto (model card (opens in a new tab))
Weights plus the KV cache of one request (BF16 cache), in GiB. Add 1 to 3 GiB for the inference engine itself.
| Weights format | Weights only | + 8K context | + 32K context | + 128K context | + 256K context |
|---|---|---|---|---|---|
| FP8 (native) | 113 | 113 | 113 | 115 | 118 |
| BF16 / FP16 | 222 | 223 | 223 | 225 | 228 |
| FP8 / INT8 | 112 | 112 | 113 | 115 | 118 |
| 4-bit (GGUF Q4_K_M) | 67.0 | 67.2 | 67.7 | 69.8 | 72.6 |
Exact size of each quantization in GZGavinZhao/Leanstral-1.5-119B-A6B-GGUF (opens in a new tab), and the smallest GPU that runs it with llama.cpp, Ollama or LM Studio and an 8K-token context.
| Quantization | File size | Smallest GPU |
|---|---|---|
| BF16 | 222 GiB | More than 96 GB: see the calculator |
| Q6_K | 91.0 GiB | RTX PRO 6000 Blackwell (96 GB) |
| Q4_K_M | 67.2 GiB | RTX PRO 6000 Blackwell (96 GB) |
Read every day from Hugging Face. Split files are added together; vision projectors are left out.
Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.
| GPU | FP8 (native) | BF16 / FP16 | 8-bit | 4-bit |
|---|---|---|---|---|
| GeForce RTX 4090 24 GB | Not on this GPU | 16 (several machines) | 6 | 4 |
| GeForce RTX 5090 32 GB | Not on this GPU | 8 | 4 | 3 |
| RTX PRO 6000 Blackwell 96 GB | Not on this GPU | 3 | 2 | 1 |
| Mac M5 Max 128 GB 96 GB usable | Not on this GPU | 3 | 2 | 1 |
| Ryzen AI Max+ 395 128 GB 96 GB usable | Not on this GPU | 3 | 2 | 1 |
| DGX Spark (GB10) 128 GB | Not on this GPU | 2 | 1 | 1 |
| NVIDIA H100 80 GB | 2 | 4 | 2 | 1 |
| NVIDIA H200 141 GB | 1 | 2 | 1 | 1 |
| NVIDIA B200 (HGX) 180 GB | 1 | 2 | 1 | 1 |
8-bit: FP8 with vLLM (INT8 on GPUs without FP8), Q8_0 with llama.cpp. 4-bit: AWQ / GPTQ with vLLM, Q4_K_M with llama.cpp, both counted at the Q4_K_M size. Not on this GPU: the official FP8 weights do not run there (llama.cpp needs a GGUF version, and vLLM needs a GPU with FP8 support).
For each GPU: the fewest cards that fit Leanstral 1.5 119B-A6B with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-10-30).
| Setup | Per hour | Weights | Provider | Per month | Rent |
|---|---|---|---|---|---|
| 5 × RTX A4000 16 GB | $0.360 | Q4_K_M | Vast.ai | $262.80 | Rent 5 × RTX A4000 on Vast.ai (opens in a new tab) → |
| 4 × GeForce RTX 3090 24 GB | $0.484 | Q4_K_M | Vast.ai | $353.32 | Rent 4 × GeForce RTX 3090 on Vast.ai (opens in a new tab) → |
| 5 × NVIDIA L4 24 GB | $0.520 | 4-bit | Vast.ai | $379.60 | Rent 5 × NVIDIA L4 on Vast.ai (opens in a new tab) → |
| 1 × NVIDIA A100 80GB | $0.630 | 4-bit | Vast.ai | $459.90 | Rent 1 × NVIDIA A100 80GB on Vast.ai (opens in a new tab) → |
| 4 × RTX A5000 24 GB | $0.756 | Q4_K_M | Vast.ai | $551.88 | Rent 4 × RTX A5000 on Vast.ai (opens in a new tab) → |
| 2 × RTX A6000 48 GB | $0.802 | Q4_K_M | Vast.ai | $585.46 | Rent 2 × RTX A6000 on Vast.ai (opens in a new tab) → |
| 2 × NVIDIA L40S 48 GB | $0.934 | 4-bit | Vast.ai | $681.82 | Rent 2 × NVIDIA L40S on Vast.ai (opens in a new tab) → |
| 2 × NVIDIA A40 48 GB | $0.934 | 4-bit | Vast.ai | $681.82 | Rent 2 × NVIDIA A40 on Vast.ai (opens in a new tab) → |
On-demand prices from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.
AWS, Google Cloud and UpCloud prices: Spare Cores (opens in a new tab), CC BY-SA 4.0 (opens in a new tab), shared under the same license.
Reasoning. Adjustable reasoning effort. Reasoning tokens take context and KV cache like any other token: leave room for them.
Architecture: Lean 4 prover · MoE 128 experts + 1 shared · MLA (256 + 64 latent) on 36 layers. Its cache stays compact because MLA stores one compressed latent per token and layer instead of full keys and values. Only 6.5B parameters are active per token, but all 119B must sit in memory: VRAM depends on the total, speed on the active part.
| Context per request | BF16 cache | FP8 cache |
|---|---|---|
| 8K tokens | 0.18 GiB | 0.09 GiB |
| 32K tokens | 0.70 GiB | 0.35 GiB |
| 128K tokens | 2.81 GiB | 1.41 GiB |
| 256K tokens | 5.63 GiB | 2.81 GiB |
In BF16 the weights alone take 222 GiB (239 GB). In FP8 that is 112 GiB, and about 67.0 GiB with 4-bit quantization (Q4_K_M); the official FP8 checkpoint is 113 GiB. Each request then adds KV cache: 0.18 GiB at 8K tokens and 0.70 GiB at 32K (BF16 cache).
No. Even in 4-bit it needs 4 RTX 4090s. In 4-bit it fits on a single RTX PRO 6000 Blackwell (96 GB).
No. Even in 4-bit it needs 3 RTX 5090s.
Yes. In 4-bit (Q4_K_M with llama.cpp) it needs a Mac with 96 GB of unified memory or more, of which macOS gives the GPU about 72 GB, for one request with an 8K-token context. In 8-bit (Q8_0) it needs 192 GB or more.
Yes. On a DGX Spark (128 GB) it fits in Q8_0 (112 GiB with an 8K-token context); on a Ryzen AI Max+ 395 with 128 GB, whose GPU gets up to 96 GB, it fits in Q4_K_M (67.2 GiB with an 8K-token context), with llama.cpp and one request.
On 2026-10-30, the cheapest on-demand setup is 5 × RTX A4000 (16 GB) with Q4_K_M weights on Vast.ai, at $0.360 per hour (about $262.80 per month). Next: 4 × GeForce RTX 3090 (24 GB) with Q4_K_M weights on Vast.ai, at $0.484 per hour. Sized for one 8K-token request; prices are checked every hour.
With one request and an 8K-token context: 4 in BF16, 2 in FP8 and 1 in 4-bit (vLLM, 90% of memory usable). Serving many users at once needs more memory for their KV caches: the calculator sizes that for you.
Yes, Leanstral 1.5 119B-A6B supports tool (function) calling: it can ask your application to run a function and use the result.
Adjustable reasoning effort. Reasoning tokens count toward the context and the KV cache.
For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/leanstral-1-5.json.
Mistral AI, France · Released July 2, 2026[](https://studiotvai.com/vram-requirements/leanstral-1-5)Same family (large moe): MiniMax M3.1 Flash · MiniMax M3 · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · Atria Dawn · Atria Dawn Preview · Hy4 Preview · K-EXAONE 2.0 750B-A37B · Inkling · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Muse Spark Open · Beam 1.0 501B-A23B · Kimi K3 · Mistral Large 4 · Mistral Large 3 · Mistral Small 4 119B · Mixtral 8x22B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Intern S2 397B · DeepSeek V3 · DeepSeek V3.1 · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · GLM-4.7 · GLM-4.5 · Ling-3.1-flash · Step 5 Preview · Hy3
Llama 3.1 8B · Llama 3 8B · Llama 3.2 3B · Nanbeige4.3 33B · Granite 4.2 30B · Granite 4.2 8B · Granite 4.2 3B · MiniCPM5 2B · MiniCPM5 1B · Ministral 3 14B · Ministral 3 8B · Ministral 3 3B · Devstral 2 123B · Devstral Small 2 24B · Mistral Medium 3.5 128B · Magistral Small 1.2 24B · Mistral Small 3 24B · Mistral Large 2411 123B · Pixtral Large 124B · Codestral 22B · Mistral Small 2409 22B · Pixtral 12B · Nemotron 3.5 Parse · Gemma 2 9B · Gemma 3 4B · LLaVA 1.6 Mistral 7B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 405B · Hy-Memory 30B-A3B · Kimi VL A3B Instruct · Mixtral 8x7B · Unlimited-OCR · Unlimited-OCR 2 · Xing4.0 29B-A4B · Qwen3.5 4B · MiniCPM-V-4.7 1B · Raon-1 mini preview · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · LFM3 1.7B · LFM3-VL 2B · d1 2B · LFM2.5 8B-A1B · LFM2 24B-A2B · Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Scout 17B-16E · Llama 4 Maverick 17B-128E · Kolibri-1 · Recursive Flint · Nemotron Labs Dory 1.0 4B · Step 3.5 Flash · Step 3.7 Flash · Laguna S 2.1 · Laguna XS 2.1 · Command A+ · Inkling Small · Muse Glimmer 30B · Nemotron 3 Nano 30B-A3B · Nemotron 3 Super 120B-A12B · Nemotron 3 Ultra 550B-A55B · Mamba-Codestral 7B · Nemotron 3.5 Super VL 120B-A12B · Nemotron 3.5 Bolt 74B-A9B · MiniMax M3.1 Flash · MiniMax M3 · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · Atria Dawn · Atria Dawn Preview · Hy4 Preview · K-EXAONE 2.0 750B-A37B · Inkling · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Muse Spark Open · Beam 1.0 501B-A23B · Kimi K3 · Mistral Large 4 · Mistral Large 3 · Mistral Small 4 119B · Mixtral 8x22B · Qwen3-Coder-Next 80B-A3B · Qwen3-Coder 30B-A3B · Qwen3-Coder 480B-A35B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Intern S2 397B · Clef · Clef Flash · d1 3B · Humanizer · JEV 27B VL · Mellum2.1 12B-A2.5B · LightOnOCR-3 4B · Spark-X2.5 4B · Agnes-3.0-Qwen · Youtu-Parsing-Omni · Agnes-3.0-Flash · Mistral 7B v0.3 · Mistral Small 3.1 24B · Mistral Nemo · Ministral 8B · DeepSeek V3 · DeepSeek R1 Qwen3 8B · DeepSeek R1 Distill Qwen 32B · DeepSeek V3.1 · DeepSeek R1 Distill Qwen 14B · DeepSeek R1 Distill Qwen 7B · DeepSeek R1 Distill Llama 8B · Qwen3 4B · Qwen3 8B · Qwen2.5 7B · Qwen3 14B · Qwen2.5 3B · Qwen3.6 27B · Qwen3.5 27B · Qwen2.5-Coder 7B · Qwen2.5 32B · Qwen2.5-Coder 14B · Qwen3.5 35B-A3B · Qwen3 30B-A3B · Qwen2.5 14B · Qwen2.5-Coder 32B · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen2.5-Coder 3B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · Gemma 4 E4B · Gemma 4 E2B · Nemotron 3 Nano 4B · Nemotron 3.5 Lightning 30B-A3B · MiniCPM-V-4.7 35B-A3B · LFM2.5 24B-A2B · GLM-4.7 · Qwen3-VL 8B · Qwen2.5-VL 7B · Qwen3-VL 4B · Qwen2.5-VL 3B · Qwen2.5-VL 32B · Qwen2-VL 7B · GLM-4.5-Air · GLM-4.5 · phi-4 · Phi-3.5-mini · Phi-4-mini · Phi-3-mini-128k · Ling-3.1-flash · Step 5 Preview · Hy3 · Ornith-1.5 122B · Spark-X2.6 4B · Sage-A1.5 · MLExpert · Agents-A1 4B · Ling-3.0-flash-Sante · MiniCPM-OCR-1.0 · WeVisOne-VL 4B · Granite 4.1 3B
Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.