LLMs · Mistral AI

Codestral Mamba 7B

Name: Codestral Mamba 7B
Author: Mistral AI

Parameters: 7.3B
Architecture: Dense
Max context: 256K tokens
License: apache-2.0
Released: 2024-07

How to run it

Original weights · Hugging Face

Full-precision files from Mistral AI, for fine-tuning, vLLM, Transformers.

huggingface.co/mistralai/Mamba-Codestral-7B-v0.1 (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run Codestral Mamba 7B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically 20–35% faster than GGUF for a model with 7.3B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Text Generation WebUI

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Jan	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX	Get Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model mlx-community/Mamba-Codestral-7B-v0.1-4bit`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve mistralai/Mamba-Codestral-7B-v0.1`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path mistralai/Mamba-Codestral-7B-v0.1`
Docker Model Runner	CLI + API	Original weights	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/mistralai/Mamba-Codestral-7B-v0.1`
Unsloth Desktop	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Get Unsloth Desktop
Atomic Chat	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
Pi	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
Hermes Agent	Assistant	MLX	macOSWSLWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
OpenClaw	Assistant	MLX	macOSWSLWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
OpenCode	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Codex CLI	Coding agent	MLX	macOSWSLWindowsLinux	uses Ollama or any OpenAI-compatible server	Point it at a llama.cpp or MLX LM server
OpenHands	Coding agent	MLX	macOSWSLWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Zed	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Cline	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Open Interpreter	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Goose	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Aider	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Crush	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Qwen Code	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Kilo Code	Coding agent	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Open WebUI	Assistant	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Khoj	Assistant	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Letta	Assistant	MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Text Generation WebUI	Desktop app	Original weights	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
Msty Studio	Desktop app	MLX	macOSWindowsLinux	Ollama, llama.cpp, MLX	Get Msty Studio
Inferencer	Desktop app	MLX	macOS	MLX	Get Inferencer
exo	Server	MLX	macOSLinux	MLX	Get exo
Continue	Coding agent	MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
SillyTavern	Assistant	MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
LibreChat	Assistant	MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
Cherry Studio	Assistant	MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
Chatbox	Assistant	MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
PrivateGPT	Assistant	MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

KV cache: state-space model: no KV cache, just a small fixed-size state.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	2.9 GB	3.5 GB	3.7 GB	All files (opens in a new tab)
`Q3_K_M`	Low	3.6 GB	4.2 GB	4.3 GB	All files (opens in a new tab)
`Q4_K_M`	Good	4.4 GB	5.1 GB	5.2 GB	All files (opens in a new tab)
`Q5_K_M`	High	5.2 GB	5.8 GB	5.9 GB	All files (opens in a new tab)
`Q6_K`	High	6.0 GB	6.6 GB	6.7 GB	All files (opens in a new tab)
`Q8_0`	Very high	7.7 GB	8.4 GB	8.5 GB	All files (opens in a new tab)
`F16`	Full	14.6 GB	15.2 GB	15.3 GB	Original weights (opens in a new tab)

Best hardware for Codestral Mamba 7B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q3_K_M.

Quality	Hardware	Quant	Memory	Speed	Runs
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 SUPER	`Q8_0`	9.0 GB / 12.0 GB	43.2 tok/s	Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4060	`Q4_K_M`	5.5 GB / 8.0 GB	45.8 tok/s	Runs great
35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	Intel Arc B580	`Q6_K`	7.2 GB / 12.0 GB	40.7 tok/s	Runs great
35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3060 12GB	`Q6_K`	7.2 GB / 12.0 GB	42.1 tok/s	Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`Q8_0`	9.2 GB / 16.0 GB	47.2 tok/s	Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 Ti SUPER	`Q8_0`	9.2 GB / 16.0 GB	57.6 tok/s	Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`Q8_0`	9.2 GB / 16.0 GB	63.1 tok/s	Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5070 Ti	`Q8_0`	9.2 GB / 16.0 GB	76.8 tok/s	Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`Q8_0`	9.2 GB / 16.0 GB	82.3 tok/s	Runs great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`F16`	16.8 GB / 32.0 GB	70.8 tok/s	Runs great

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.