Mistral Medium 3.5 128B
127.7B parameters · 256k context · Modified MIT License · released 2026-03-31
chatcodingagenticvisionreasoning
In short
Mistral Medium 3.5 128B is an open model from Mistral AI with 127.7B parameters. At Q4_K_M, Mistral Medium 3.5 128B needs about 73 GB of memory at 8k context and 115 GB at 128k, counting the weights, the KV cache and runtime buffers. Nothing we price in Germany runs Mistral Medium 3.5 128B fully in memory at 128k context at a usable speed; see the table for what comes closest.
Updated . Speeds are estimates; how they are worked out.
What to run it on in Germany
Fully in memory at 128k context, priced at retailers today.
Something we price holds it fully in memory, but none reaches 15 tok/s, our bar for recommending it. The table below has the speeds.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
| Hardware | Quant | Fits | Decode | Price | tok/s per 1,000 |
|---|---|---|---|---|---|
| NVIDIA DGX Spark 128GB | Q4_K_M | fits | 1 tok/s | 8.313 € | 0.2 |
| ASUS Ascent GX10 128GB | Q4_K_M | fits | 1 tok/s | 8.623 € | 0.2 |
| Mac Studio M3 Ultra 256GB | Q8_0 | fits | 3 tok/s | 15.555 € | 0.2 |
| Mac Studio M3 Ultra 512GB | Q8_0 | fits | 3 tok/s | 18.995 € | 0.2 |
| NVIDIA RTX PRO 6000 Blackwell | Q4_K_M | offload | 2 tok/s | 19.076 € | 0.1 |
35 other cards and machines we price cannot hold it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File | @8k | @32k | @64k | @128k |
|---|---|---|---|---|---|
| Q4_K_Mgguf | 69.8 GB | 73.3 GB | 81.6 GB | 92.8 GB | 115.2 GB |
| Q5_K_Mgguf | 82.3 GB | 85.7 GB | 94.1 GB | 105.3 GB | 127.7 GB |
| Q6_Kgguf | 95.5 GB | 99.0 GB | 107.4 GB | 118.6 GB | 141.0 GB |
| Q8_0gguf | 123.7 GB | 127.2 GB | 135.6 GB | 146.8 GB | 169.2 GB |
Run it
Copy a command for the runtime you use.
- Q4_K_M
- Ollama
ollama run hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:Q4_K_M - LM Studio
lms get unsloth/Mistral-Medium-3.5-128B-GGUF@q4_k_m - llama.cpp
llama-server -hf unsloth/Mistral-Medium-3.5-128B-GGUF:Q4_K_M
- Ollama
- Q5_K_M
- Ollama
ollama run hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:Q5_K_M - LM Studio
lms get unsloth/Mistral-Medium-3.5-128B-GGUF@q5_k_m - llama.cpp
llama-server -hf unsloth/Mistral-Medium-3.5-128B-GGUF:Q5_K_M
- Ollama
- Q6_K
- Ollama
ollama run hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:Q6_K - LM Studio
lms get unsloth/Mistral-Medium-3.5-128B-GGUF@q6_k - llama.cpp
llama-server -hf unsloth/Mistral-Medium-3.5-128B-GGUF:Q6_K
- Ollama
- Q8_0
- Ollama
ollama run hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:Q8_0 - LM Studio
lms get unsloth/Mistral-Medium-3.5-128B-GGUF@q8_0 - llama.cpp
llama-server -hf unsloth/Mistral-Medium-3.5-128B-GGUF:Q8_0
- Ollama
Notes
The original Transformers config had a bug that degraded long-context performance, and GGUFs made before the fix commit are also affected. The vLLM recipe uses tensor-parallel-size 8 and needs vLLM nightly, mistral_common >= 1.11.1 and transformers >= 5.4.0.
Questions
- How much VRAM does Mistral Medium 3.5 128B need?
- At Q4_K_M, Mistral Medium 3.5 128B needs about 73 GB of memory at 8k context and 115 GB at 128k, counting the weights, the KV cache and runtime buffers.
- Can I run Mistral Medium 3.5 128B on a 16 GB GPU?
- No: it does not fit in 16 GB at 128k context, even with system RAM.
- Can I run Mistral Medium 3.5 128B on a 24 GB GPU?
- No: it does not fit in 24 GB at 128k context, even with system RAM.
- How do I run Mistral Medium 3.5 128B locally?
- With Ollama: ollama run hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:Q4_K_M (the Q4_K_M build). LM Studio and llama.cpp commands are on this page.
- What licence is Mistral Medium 3.5 128B released under?
- Modified MIT License.