Magistral Small 1.2 24B
24BMistral Magistral
Mistral's reasoning model on a Mistral Small 3.2 base, with reasoning wrapped in [THINK] tags. At Q4_K_M it needs about 15.7 GB at 4K, tight on a 16 GB card and comfortable on 20 GB — explicit chain-of-thought a level below the 70B-class reasoners most guides assume.
131K
Max Context
5
Quant Variants
GGUF Q6_K
Best Quality
+0.6%
Perplexity rise (best build)
Quantization Variants
Per-quant VRAM, quality loss, and inference speed on RTX 4090
Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports
| Format | Level | BPW | VRAM | PPL Loss | Speed | Source | Actions |
|---|---|---|---|---|---|---|---|
| GGUF | Q4_K_M | 4.86 | 15.7 GB | 2.9% | 60 tok/s | Community | |
| GGUF | Q5_K_M | 5.69 | 18.2 GB | 1.4% | 54 tok/s | Estimated | |
| GGUF | Q6_K | 6.56 | 20.9 GB | 0.6% | 47 tok/s | Estimated | |
| AWQ | INT4 | 4 | 13.0 GB | 4.0% | 76 tok/s | Estimated | |
| EXL2 | 4.65bpw | 4.65 | 15.0 GB | 2.5% | — | Estimated |
Which file each size is for
A file size is not a memory figure: the VRAM column is the calculator's total at 4K context — weights plus KV cache plus a 10% activation buffer. Units differ on purpose: file sizes are decimal GB, as Hugging Face lists them; the VRAM column is GiB (1024³ bytes) with 2% added to the weights, so 7.12 GB of file counts as about 6.8 GiB there. A vision projector (mmproj), where the repo ships one, is a separate download and is in neither number.
- GGUF Q4_K_Mbartowski/mistralai_Magistral-Small-2509-GGUF · mistralai_Magistral-Small-2509-Q4_K_M.gguf · 14.33 GB (14,333,912,032 bytes) · listing read 2026-11-03
- GGUF Q5_K_Mbartowski/mistralai_Magistral-Small-2509-GGUF · mistralai_Magistral-Small-2509-Q5_K_M.gguf · 16.76 GB (16,763,986,912 bytes) · listing read 2026-11-03
- GGUF Q6_Kbartowski/mistralai_Magistral-Small-2509-GGUF · mistralai_Magistral-Small-2509-Q6_K.gguf · 19.35 GB (19,345,941,472 bytes) · listing read 2026-11-03
- AWQ INT4Sized at the calculator's generic rate for this level; no file was checked.
- EXL2 4.65bpwSized at the calculator's generic rate for this level; no file was checked.
Related community runs
These runs describe their own settings. Their speeds do not replace this estimate or prove your configuration fits.
Our reviewed link index has no run for this model yet. You can browse community reports or share your own test below.
Browse more runs on llamaPerf ↗Similar models
Compare with Qwen3-VL 30B-A3BQwen3-VL 30B-A3B Instruct
Alibaba Qwen3-VL
Multimodal MoE with only ~3B active parameters, so it stays responsive on Apple unified memory and survives CPU offload far better than a dense 30B. At Q4_K_M it needs about 19.9 GB at 4K, comfortable on a 24 GB card; Q3_K_M brings that to 15.1 GB. The vision encoder is a separate 1.1 GB file.
Gemma 4 26B-A4B IT
Google Gemma 4
Google's Gemma 4 mixture-of-experts model: about 25B parameters in the text model, roughly 4B active per token, a 256K window and image input. Only 5 of its 30 layers keep a cache that grows with context, and those use fewer, wider heads, so the cache stays small — about 0.9 GB at 32K and 5.3 GB at the full 256K. At Q4_K_M that is about 18.8 GB at 32K: comfortable on a 24 GB card, which can still load the whole window (tight, about 23.6 GB). A 16 GB card cannot hold it, since the Q4_K_M file alone is 17.0 GB. The vision encoder is a separate 1.2 GB file on top. Sizes come from bartowski's GGUF files, whose Q4_K_M works out at 5.40 bits per weight, well above the generic 4-bit rate; Unsloth's UD-Q4_K_M is a different file, 0.09 GB smaller. No per-level quality loss has been published.
Gemma 4 31B IT
Google Gemma 4
Google's dense Gemma 4 flagship: about 31B parameters, a 256K window and image input. Only 10 of its 60 layers cache the full context, and those use four wide KV heads, so 128K of context adds about 11 GB of cache where a conventional 60-layer design would need about 120 GB. At Q4_K_M it needs about 22.1 GB at 4K, tight on a 24 GB card; Q3_K_M is about 18.3 GB at 4K. A 32 GB card holds Q4_K_M at 32K comfortably. Google also publishes its own quantization-aware (QAT) Q4_0 build, a single 17.7 GB file: about 20.1 GB at 4K, comfortable on 24 GB up to 16K. Its 1.2 GB vision encoder is a separate file, and with it loaded even 4K is tight on 24 GB. The other levels are sized from bartowski's GGUF files, and no per-level quality loss has been published. That repository also carries two MTP draft-head files (349 MB at Q4_0, 515 MB at Q8_0) for speculative decoding; they are not the model itself and are not counted in these sizes.
Muse Glimmer 30B
Meta Muse
Meta's first open-weight model since Llama 4, released in August under Apache 2.0 and built to run on one card. It is a dense model: a 28B text decoder that reads images through a separate vision encoder and answers in text. Three of every four layers use a 2K sliding window and the rest share just 2 KV heads, so long context is unusually cheap. At Q4_K_M it needs about 17.7 GB at 4K context and only 19.4 GB at its full 128K window, comfortable on a 24 GB card either way. Q5_K_M is tight on 24 GB, and Q8_0 wants a 32 GB card. The vision encoder (about 1.4 GB as a GGUF mmproj file) and Meta's optional speculative-decoding drafter load on top and are not included. Sizes come from the published GGUF file sizes; the Q4_K_M row is Meta's own official build. Meta's benchmark claims are its own, and no per-level quality loss has been published.
Running Magistral Small 1.2 24B locally
At Q4_K_M and 4K of context, Magistral Small 1.2 24B needs about 15.7 GB — 13.6 GB of weights, 0.63 GB of KV cache and a 1.4 GB activation buffer. The smallest card in this index that clears that comfortably is the Radeon RX 7900 XT at 20 GB, and 35 of the 105 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.
What longer context costs
Going from 4K to 32K adds about 4.37 GB, taking the total to 20.5 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4_K_M would need about 37 GB.
Which build to download
This index tracks 3 formats for it — GGUF, AWQ, EXL2 — across 5 levels. Q6_K carries the lowest published perplexity loss at 0.6%. The fastest level listed is AWQ INT4 at about 76 tok/s on an RTX 4090, batch 1 — an estimate, not a run on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.
Common questions
- How much VRAM does Magistral Small 1.2 24B need?
- About 15.7 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 20.5 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
- Will Magistral Small 1.2 24B run on a 20GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 15.7 GB, which leaves 4.3 GB spare on a Radeon RX 7900 XT. That is the smallest card in this index that clears it comfortably; 35 of 105 do.
- Which quantization of Magistral Small 1.2 24B should I use?
- Q6_K has the lowest published quality loss (0.6%), and Q4_K_M is the level most people run. All 5 levels in the index are Q4_K_M, Q5_K_M, Q6_K, AWQ INT4, EXL2 4.65bpw.
Where this model fits
Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.
- Runs comfortably on
- Radeon RX 7900 XT20GB · +4.3Mac M4 24G24GB · +2.3Mac M4 Pro 24G24GB · +2.3RTX 309024GB · +8.3Radeon RX 7900 XTX24GB · +8.3
- Tight but possible
- RTX 4060 Ti 16G16GBRadeon RX 7600 XT16GBRadeon RX 9060 XT 16G16GB
- Compared here
- GGUF vs AWQGGUF vs EXL2AWQ vs EXL2
- Try it yourself
- Size it in the calculatorGenerate the run command
Cards for this model
- RTX 5090
- RTX 5080
- RTX 5070 Ti
- RTX 5060 Ti 16G
- RTX 4090
- RTX 4080 Super
- RTX 4070 Ti Super
- RTX 4060 Ti 16G
- RTX 3090
- A100 80G
- A100 40G
- L40S 48G
- A40 48G
- H100 80G
- DGX Spark 64G
- Tesla P100 16G
- Tesla P40 24G
- Mac M5 Pro 64G
- Mac M5 32G
- Mac M4 Max 36G
- Mac M4 Pro 48G
- Mac M4 Pro 24G
- Mac M3 Max 48G
- Mac M3 Pro 36G
- Mac M4 24G
- Mac M1 Max 64G
- Mac M2 Max 96G
- Radeon RX 9070 XT
- Radeon RX 9070
- Radeon RX 9060 XT 16G
- Radeon RX 7900 XTX
- Radeon RX 7900 XT
- Radeon RX 7900 GRE
- Radeon RX 7800 XT
- Radeon RX 7600 XT
- Radeon RX 6900 XT
- Radeon RX 6800 XT
- Radeon PRO W7900 48G
- Radeon AI PRO R9700 32G
- Instinct MI100 32G
- Arc A770 16G
- Arc Pro B70 32G
How to actually run this
Deployment guides for this model and this class of hardware.
This page's figures change when the model or the runtime does.Last updated 2026-11-22 RSS → /feed.xml