Model memory guides / mistralai/Mistral-Large-Instruct-2411
mistralai/Mistral-Large-Instruct-2411 VRAM estimates
For mistralai/Mistral-Large-Instruct-2411, compare how precision and context change memory planning for text generation.
What changes the memory requirement?
In the Q4_K_M scenario (4.85 effective bits/weight), reported parameters account for approximately 69.23 GiB of weights. At 2,048 tokens, cache and recurrent state add 0.69 GiB. At 32,768 tokens, they add 11.00 GiB. The metadata declares a maximum context of 131,072 tokens; this is not a guarantee of useful output quality at that length.
Reported parameters
122.61 billion
Cache architecture
mistral
Metadata snapshot
2026-08-31
Weight, cache and planning totals
One sequence, F16 cache, full residency on one device. Context includes both prompt and generated tokens. All memory values are GiB (2³⁰ bytes).
| Precision / effective BPW | Context tokens | Weights | Cache & state | Planning total (+1 GiB budget) | Adjust |
|---|---|---|---|---|---|
| Q4_K_M scenario4.85 bits/weight | 2,048 | 69.23 | 0.69 | 70.91 | Calculator |
| Q4_K_M scenario4.85 bits/weight | 8,192 | 69.23 | 2.75 | 72.98 | Calculator |
| Q4_K_M scenario4.85 bits/weight | 32,768 | 69.23 | 11.00 | 81.23 | Calculator |
| Q8_0 scenario8.5 bits/weight | 2,048 | 121.33 | 0.69 | 123.01 | Calculator |
| Q8_0 scenario8.5 bits/weight | 8,192 | 121.33 | 2.75 | 125.08 | Calculator |
| Q8_0 scenario8.5 bits/weight | 32,768 | 121.33 | 11.00 | 133.33 | Calculator |
| 16-bit scenario16 bits/weight | 2,048 | 228.38 | 0.69 | 230.07 | Calculator |
| 16-bit scenario16 bits/weight | 8,192 | 228.38 | 2.75 | 232.13 | Calculator |
| 16-bit scenario16 bits/weight | 32,768 | 228.38 | 11.00 | 240.38 | Calculator |
Q4_K_M and Q8_0 here are assumed effective-BPW scenarios, not inspected GGUF files. Tensor mixtures and conversions can change actual weight storage. The calculator lets you inspect an actual artifact and choose your GPU before presenting a personalized result.
How these numbers are calculated
Weights = reported parameter count × effective bits per weight ÷ 8. Cache and state use the architecture-specific equations in the same engine as our calculator. Planning total = weights + cache/state + the stated runtime budget. For MoE, full residency includes all experts, not just active parameters per token.
Profile: llama.cpp / CUDA, Flash Attention enabled, micro-batch 512, prompt batch 2,048, no recurrent rollback snapshots. Engine 3.5.0; pinned runtime source. Multi-GPU, partial offload, training, speculative decoding and image/audio processing are outside these scenarios.
Model-specific assumptions and limitations
- Weights use parameter count × assumed effective BPW; mixed tensor types and conversion can change artifact size.
- Runtime allowance is an editable planning budget, not a measured compute-buffer prediction or an error bound.
- No model execution or hardware compatibility is certified. Available device memory may be lower than listed capacity.
Sources and reproducibility
Configuration at the pinned model revision · Model repository at that revision · Equations and external evidence
The parameter count and configuration come from our bundled metadata snapshot. This page is generated from that snapshot; it does not claim a live metadata check or a GPU benchmark.
Revision: ba78820945ae22361b0274cf0ae6d696c967c1a4. Open a table scenario to inspect that revision in the calculator.
Compare other models
- mistralai/Mistral-Small-Instruct-2409 — 22.247B parameters, mistral
- Qwen/Qwen3-Coder-Next — 79.674B parameters, qwen3_next
- meta-llama/Llama-3.3-70B-Instruct — 70.554B parameters, llama