Mistral Small 4 (119B-2603)
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M bartowski/mistralai_Mistral-Small-4-119B-2603-GGUF | 67.65 GiB | 2 | unknown | 80 GB GPU (cache unknown) | HF files |
| Q5_K_M bartowski/mistralai_Mistral-Small-4-119B-2603-GGUF | 79.20 GiB | 3 | unknown | 96 GB GPU (cache unknown) | HF files |
| Q8_0 bartowski/mistralai_Mistral-Small-4-119B-2603-GGUF | 118 GiB | 4 | unknown | 128 GB GPU (cache unknown) | HF files |
| BF16 unsloth/Mistral-Small-4-119B-2603-GGUF | 222 GiB | 6 | unknown | over 192 GB GPU | HF files |
No verified file: FP16, MLX 4-bit, MLX 8-bit. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.
Quality
Artificial Analysis Intelligence Index
11.3
Variant: Mistral Small 4 (Reasoning) · observed 2026-10-17 · source
Rank #55 of 75 researched 2026 models.
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 2
| Hardware | Quant | Backend | Prompt t/s | Gen t/s | Date | Source |
|---|---|---|---|---|---|---|
| Apple M5 Max (40-core GPU), 128 GB unified memory | MLX 4-bit | MLX | 1,507 | 86.8 | 2026-10-07 | omlx.ai |
| Apple M1 Ultra (48-core GPU), 128 GB unified memory | MLX 4-bit | MLX | 458 | 46.5 | 2026-10-02 | omlx.ai |
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database