Mistral-Nemo-Instruct-2407 VRAM & Memory Requirements
Specific checkpoints with sourced architecture and weight files. GGUF Q4_K_M (Unsloth): 8.34 GiB–8.94 GiB at 8,192 tokens, 1 sequence, FP16 KV, llama.cpp.
This result is an estimate, not a measured trace.Not verifiedFile-backed weights
Runs on
Publisher and provenance
- PublisherMistral AI
- Hugging Face
mistralai/Mistral-Nemo-Instruct-2407 - Revision
04d8a90549d23fc6bd7f642064003592df51e9b3 - Total parameters12,247,782,400
- Layers40
- Query heads32
- KV heads8 (gqa)
- Head dimension128
- Recorded context capability131,072
- Completenesscomplete · full
Memory layers in this estimate
Artifact bytes, raw KV, engine extras, and total demand are separate. This is not a runtime trace.
- Weight artifact
- 6.96 GiB (7,477,204,512 bytes)
- Raw KV cache
- 1.25 GiB (1,342,177,280 bytes)
- Engine extras / workspace
- 0.13 GiB–0.73 GiB
- Total estimated demand
- 8.34 GiB–8.94 GiB
Published artifacts
| Quantization | Selected files | Bytes | Engine | Evidence |
|---|---|---|---|---|
| BF16 safetensors bf16 | 24,495,564,800 (22.81 GiB / 24.50 GB) | vllm, sglang, unspecified | file-metadata | |
| GGUF Q4_K_M (Unsloth) gguf-q4_k_m | Mistral-Nemo-Instruct-2407.Q4_K_M.gguf | 7,477,204,512 (6.96 GiB / 7.48 GB) | llama.cpp, ollama, unspecified | file-metadata |
| GGUF Q5_K_M (Unsloth) gguf-q5_k_m | Mistral-Nemo-Instruct-2407.Q5_K_M.gguf | 8,727,631,392 (8.13 GiB / 8.73 GB) | llama.cpp, ollama, unspecified | file-metadata |
| GGUF Q6_K (Unsloth) gguf-q6_k | Mistral-Nemo-Instruct-2407.Q6_K.gguf | 10,056,209,952 (9.37 GiB / 10.06 GB) | llama.cpp, ollama, unspecified | file-metadata |
| GGUF Q8_0 (Unsloth) gguf-q8_0 | Mistral-Nemo-Instruct-2407.Q8_0.gguf | 13,022,369,312 (12.13 GiB / 13.02 GB) | llama.cpp, ollama, unspecified | file-metadata |
| INT4 theoretical | No published file | 6,123,891,200 (theoretical) | — | theoretical |
Memory by quantization and context
Concurrent sequences = 1. KV defaults to FP16. The range includes documented runtime extras for the listed engine. These figures use the same core as the interactive calculator.
| Quantization | 2,048 tokens | 8,192 tokens | 32,768 tokens |
|---|---|---|---|
| BF16 safetensors | 23.75 GiB–25.64 GiB | 24.69 GiB–26.60 GiB | 28.44 GiB–30.46 GiB |
| GGUF Q4_K_M (Unsloth) | 7.40 GiB–7.92 GiB | 8.34 GiB–8.94 GiB | 12.09 GiB–12.95 GiB |
| GGUF Q5_K_M (Unsloth) | 8.57 GiB–9.11 GiB | 9.50 GiB–10.13 GiB | 13.25 GiB–14.14 GiB |
| GGUF Q6_K (Unsloth) | 9.80 GiB–10.37 GiB | 10.74 GiB–11.39 GiB | 14.49 GiB–15.40 GiB |
| GGUF Q8_0 (Unsloth) | 12.57 GiB–13.19 GiB | 13.50 GiB–14.21 GiB | 17.25 GiB–18.22 GiB |
| INT4 theoretical Theoretical rows are not downloadable artifacts. | 6.14 GiB–8.29 GiB | 7.08 GiB–9.46 GiB | 10.83 GiB–14.07 GiB |
Raw KV contribution
Standard GQA/MHA raw KV is 2 × layers × kvHeads × headDim × tokens × sequences × bytes per element. This page uses KV heads (8), not query heads (32). Using query heads would overstate this cache by 4×.
- 8,192 tokens, 1 sequence, FP16: 1,342,177,280 bytes (1.2500 GiB)
- 32,768 tokens: 5,368,709,120 bytes (5.00 GiB)
Related pages
Sources
- Mistral-Nemo-Instruct-2407 model card
- config.json — revision 04d8a90549d23fc6bd7f642064003592df51e9b3
- safetensors index — metadata.total_size=24495564800
- Artifact repo unsloth/Mistral-Nemo-Instruct-2407-GGUF
Assumptions that affect this result
- Requested context is within the recorded native window of 131072 tokens.
- Full-resident weight estimates use total parameters, including inactive MoE experts.
- Weight bytes come from the selected weight files only, not from every file in the repository.
- Download file size is not peak GPU memory. Runtime layout, allocator padding, and KV are extra.
- Counted files: Mistral-Nemo-Instruct-2407.Q4_K_M.gguf.
- Context budget is the number of cached tokens per sequence (prompt plus reserved generation).
- Concurrent sequences share one model replica; weights are not multiplied by sequence count.
- KV dtype is independent of weight quantization unless you change it.
Calculator
Loading catalog snapshot…
Search or pick a catalog checkpoint to see memory demand.
Search or pick a catalog checkpoint to see memory demand.