readygpu

Mistral Small 4 119B

119.4B total, 7.1B active · 1024k context · apache-2.0 · released 2026-01-23

chatcodingagenticreasoningvision

What to run it on in Germany

Fully in memory at 32k 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.

HardwareQuantFitsDecodePricetok/s per 1,000
Mac Studio M4 Max 128GBUD-Q6_Kfits32 tok/s––
Mac mini M4 Pro 64GBUD-Q2_K_XLfits34 tok/s––
Framework Desktop Ryzen AI Max+ 395 128GBUD-Q6_Kfits13 tok/s––
Mac Studio M3 Ultra 512GBQ8_0fits39 tok/s––
NVIDIA DGX Spark 128GBUD-Q6_Kfits15 tok/s––
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBUD-Q6_Kfits13 tok/s––
Mac Studio M3 Ultra 256GBQ8_0fits39 tok/s––
Mac Studio M4 Max 64GBUD-Q2_K_XLfits68 tok/s––
Mac Studio M3 Ultra 96GBUD-Q4_K_Mfits62 tok/s––
NVIDIA RTX PRO 6000 BlackwellUD-Q6_Kfits101 tok/s––
ASUS Ascent GX10 128GBUD-Q6_Kfits15 tok/s––
Framework Desktop Ryzen AI Max+ 395 64GBUD-Q2_K_XLfits27 tok/s––
NVIDIA GeForce RTX 3090UD-Q2_K_XLoffload22 tok/s––
NVIDIA GeForce RTX 5090UD-Q2_K_XLoffload43 tok/s––
NVIDIA GeForce RTX 4090UD-Q2_K_XLoffload22 tok/s––
NVIDIA GeForce RTX 5070 TiUD-Q2_K_XLoffload16 tok/s––
NVIDIA GeForce RTX 5060 Ti 16GBUD-Q2_K_XLoffload15 tok/s––
AMD Radeon RX 7900 XTXUD-Q2_K_XLoffload22 tok/s––
AMD Radeon RX 9070 XTUD-Q2_K_XLoffload15 tok/s––
NVIDIA GeForce RTX 4060 Ti 16GBUD-Q2_K_XLoffload14 tok/s––
NVIDIA GeForce RTX 5080UD-Q2_K_XLoffload16 tok/s––
NVIDIA GeForce RTX 4070 Ti SuperUD-Q2_K_XLoffload15 tok/s––
AMD Radeon RX 9060 XT 16GBUD-Q2_K_XLoffload14 tok/s––
NVIDIA GeForce RTX 4080 SuperUD-Q2_K_XLoffload16 tok/s––
AMD Radeon AI PRO R9700UD-Q2_K_XLoffload31 tok/s––
AMD Radeon RX 7800 XTUD-Q2_K_XLoffload15 tok/s––
AMD Radeon RX 7900 XTUD-Q2_K_XLoffload18 tok/s––
NVIDIA GeForce RTX 3090 TiUD-Q2_K_XLoffload22 tok/s––
AMD Radeon RX 7600 XTUD-Q2_K_XLoffload14 tok/s––
Intel Arc Pro B60UD-Q2_K_XLoffload17 tok/s––
NVIDIA Tesla P40UD-Q2_K_XLoffload19 tok/s––
Intel Arc A770 16GBUD-Q2_K_XLoffload14 tok/s––

8 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).

QuantFile@8k@32k@64k@128k
UD-Q4_K_Mgguf68.7 GB69.6 GB70.3 GB71.2 GB73.0 GB
UD-Q2_K_XLgguf37.4 GB38.4 GB39.0 GB39.9 GB41.7 GB
UD-Q3_K_Mgguf50.6 GB51.6 GB52.2 GB53.1 GB54.9 GB
mlx-4bitmlx63.1 GB64.0 GB64.7 GB65.6 GB67.4 GB
UD-Q5_K_Mgguf83.0 GB84.0 GB84.6 GB85.5 GB87.3 GB
UD-Q6_Kgguf92.6 GB93.5 GB94.2 GB95.1 GB96.9 GB
Q8_0gguf117.8 GB118.7 GB119.4 GB120.3 GB122.0 GB
mlx-8bitmlx118.5 GB119.4 GB120.1 GB121.0 GB122.8 GB

Run it

Copy a command for the runtime you use.

  • UD-Q4_K_M
    • Ollamaollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q4_K_M
    • LM Studiolms get unsloth/Mistral-Small-4-119B-2603-GGUF@ud-q4_k_m
    • llama.cppllama-server -hf unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q4_K_M
  • UD-Q2_K_XL
    • Ollamaollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q2_K_XL
    • LM Studiolms get unsloth/Mistral-Small-4-119B-2603-GGUF@ud-q2_k_xl
    • llama.cppllama-server -hf unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q2_K_XL
  • UD-Q3_K_M
    • Ollamaollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q3_K_M
    • LM Studiolms get unsloth/Mistral-Small-4-119B-2603-GGUF@ud-q3_k_m
    • llama.cppllama-server -hf unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q3_K_M
  • mlx-4bit
    • LM Studiolms get mlx-community/Mistral-Small-4-119B-2603-4bit
    • MLXmlx_lm.server --model mlx-community/Mistral-Small-4-119B-2603-4bit
  • UD-Q5_K_M
    • Ollamaollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q5_K_M
    • LM Studiolms get unsloth/Mistral-Small-4-119B-2603-GGUF@ud-q5_k_m
    • llama.cppllama-server -hf unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q5_K_M
  • UD-Q6_K
    • Ollamaollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q6_K
    • LM Studiolms get unsloth/Mistral-Small-4-119B-2603-GGUF@ud-q6_k
    • llama.cppllama-server -hf unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q6_K
  • Q8_0
    • Ollamaollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:Q8_0
    • LM Studiolms get unsloth/Mistral-Small-4-119B-2603-GGUF@q8_0
    • llama.cppllama-server -hf unsloth/Mistral-Small-4-119B-2603-GGUF:Q8_0
  • mlx-8bit
    • LM Studiolms get mlx-community/Mistral-Small-4-119B-2603-8bit
    • MLXmlx_lm.server --model mlx-community/Mistral-Small-4-119B-2603-8bit