Mistral Small 4 119B 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 reads text and images, calls tools and lets you set its reasoning effort.
Read every day from Hugging Face. Split files are added together; vision projectors are left out.
How many GPUs to run Mistral Small 4 119B
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).
Cheapest way to run Mistral Small 4 119B today
For each GPU: the fewest cards that fit Mistral Small 4 119B with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-10-30).
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.
Reasoning. Adjustable reasoning effort. Reasoning tokens take context and KV cache like any other token: leave room for them.
KV cache: how memory grows with context
Architecture: MoE 128 experts + 1 shared · MLA (256 + 64 latent) on 36 layers · vision encoder. 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
Mistral Small 4 119B VRAM FAQ
How much VRAM does Mistral Small 4 119B need?
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).
Can Mistral Small 4 119B run on a single RTX 4090 (24 GB)?
No. Even in 4-bit it needs 4 RTX 4090s. In 4-bit it fits on a single RTX PRO 6000 Blackwell (96 GB).
Can Mistral Small 4 119B run on an RTX 5090 (32 GB)?
No. Even in 4-bit it needs 3 RTX 5090s.
Can Mistral Small 4 119B run on a Mac?
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.
Can Mistral Small 4 119B run on a DGX Spark or a Ryzen AI Max+ 395 (128 GB)?
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.
What is the cheapest way to run Mistral Small 4 119B?
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.
How many H100 GPUs does Mistral Small 4 119B need?
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.
Can Mistral Small 4 119B read images?
Yes. Mistral Small 4 119B reads text and images. Images add tokens to the context, so they also add KV cache.
Does Mistral Small 4 119B support tool calling?
Yes, Mistral Small 4 119B supports tool (function) calling: it can ask your application to run a function and use the result.
Does Mistral Small 4 119B have a thinking mode?
Adjustable reasoning effort. Reasoning tokens count toward the context and the KV cache.
Mistral Small 4 119B VRAM badge
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/mistral-small-4.json.
[](https://studiotvai.com/vram-requirements/mistral-small-4)
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.
Mistral AI, France · Released March 16, 2026