Mistral Nemo Instruct 2407 — Hardware Requirements & GPU Compatibility
ChatFunctions
Mistral Nemo Instruct 2407 is a 12-billion-parameter instruction-tuned chat model from Mistral AI, a dated release from July 2024. It targets general dialogue and instruction-following use cases, sitting in a practical middle ground between lightweight and large-scale models in terms of both capability and resource demands. The model offers a 128K token context window, generous for its parameter class, and is released under the Apache 2.0 license, allowing unrestricted local and commercial use. At around 12 billion parameters, Mistral Nemo Instruct 2407 fits on a single consumer GPU when quantized, putting it within easy reach of local enthusiasts running their own hardware.
Runs great on a 24 GB GPU
Runs from 8 GB (IQ2_M · 16K)Best on 24 GB (Q4_K_M · ~81 tok/s · 64K)Macs from 16 GB (Q4_K_M · ~17 tok/s)
Score 65.4#101 of 106 open#32 of 36 that fit 24 GBApache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
65.4
- 90% range 58.2–72.7
- #101 of 106 open models
- #32 of 36 that fit 24 GB
Run Mistral Nemo Instruct 2407
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 13.0 GB free · 16K context
Download: Mistral-Nemo-Instruct-2407-Q4_K_M.gguf7.48 GBbartowski
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3090 (24 GB) (13 GB headroom) · Q4_K_M
- Generation speed
- ~75 tok/s
- generation speed
- Cost per 1M output tokens
- $0.62
- per 1M output tokens
How Much VRAM Does Mistral Nemo Instruct 2407 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 5.9 GB | 12.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 64K context · ~111 tok/s | |
| 6.1 GB | 12.4 GB | 3-bit small — 3-bit small quantization | Fits: 64K context · ~108 tok/s | |
| 6.7 GB | 13 GB | 3-bit medium — 3-bit medium quantization | Fits: 64K context · ~98 tok/s | |
| 6.8 GB | 13.1 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 64K context · ~96 tok/s | |
| 8.1 GB | 14.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 64K context · ~81 tok/s | |
| 9.4 GB | 15.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 64K context · ~69 tok/s | |
| 10.8 GB | 17.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 64K context · ~61 tok/s | |
| 13.0 GB | 19.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~51 tok/s |
Selected Q4_K_M
4-bit medium quantization11.0GBat 16K context
- Weights
- 7.4 GB
- KV cache
- 3.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 13.0 GB free · ~81 tok/s
≥50 tok/s needs ≥620 GB/s · RTX 5090 ~144, RTX 3090 Ti ~81
Which Hardware Can Run Mistral Nemo Instruct 2407?
Q4_K_M · 8.1 GBMistral Nemo Instruct 2407 (Q4_K_M) requires 8.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 11+ GB is recommended. Using the full 131K context window can add up to 26.4 GB, bringing total usage to 34.5 GB. 40 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti. 150 devices with unified memory can run Mistral Nemo Instruct 2407, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
12 GB
12 GB tier →fits · 1.0 GB free · up to 16K ctx
10 GPUs
RTX 3080 Ti~74Simulate output on RTX 3080 TiRTX 5070~54Simulate output on RTX 5070RTX 4070~41Simulate output on RTX 407020 GB
fits · 9.0 GB free · up to 32K ctx
1 GPU
RX 7900 XT~60Simulate output on RX 7900 XT32–40 GB
fits · 21.0 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~144Simulate output on RTX 5090M5 Max36 GB~40Simulate output on Mac Studio M5 Max (36 GB)M532 GB~13Simulate output on MacBook Air 13" M5 (32 GB)Orin~17Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~11Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Mistral Nemo Instruct 2407?
The llmrun Score merges 4 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the 24 GB tier
- Mistral Nemo Instruct 2407
- Other models
- Best Score for its VRAM
#32 of 36 that fit 24 GB
Each dot is a model at the best quant that fits a 24 GB GPU. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.
Full 24 GB ranking →Benchmarks
Here are all 5 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- GPQA Diamond
Epoch AI · Jul 2024Independent
Independent29.9%
#84/100 open
- MMLU-Pro
TIGER-LabIndependent
Independent44.8%
#87/146 open
- MATH Level 5
Epoch AI · Jul 2024Independent
Independent10.8%
#33/39 open
- DTBench
Epoch AI · Jul 2024Lab-reported
Lab-reported48.6%
#65/70 open
- BALROG
Epoch AI · Jul 2024Independent
Independent17.6%
#6/15 open
In the 24 GB class
36 models fit 24 GBSame Score, only models that fit 24 GB at their best quant: the ranking a 24 GB owner actually chooses from.
- #1
Qwen3.8 27BAlibaba
122.0
~38 tok/s · 17.9 GB
- #2
Qwen3.6 27BAlibaba
111.2
~38 tok/s · 17.9 GB
- #3
Qwen3.6 35B A3BAlibaba
106.8
~151 tok/s · 22.0 GB
- #4
Gemma 4 31B ITGoogle
106.7
~32 tok/s · 21.7 GB
- #5
Gemma 4 26B A4B ITGoogle
105.8
~171 tok/s · 16.5 GB
- #6
Qwen3.5 35B A3BAlibaba
105.8
~151 tok/s · 22.0 GB
Alternatives to Mistral Nemo Instruct 2407
Mistral family · 35 models →Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.
Best alternative at this size
GPT OSS 20B
OpenAI
- 31 higher Score
- 2.1 GB more VRAM
- 108 tok/s faster
Score 96.4 · 13.1 GB · ~190 tok/s
Much faster, similar quality
Qwen3.6 35B A3B
Alibaba
- 41.4 higher Score
- 11 GB more VRAM
- 70 tok/s faster
Score 106.8 · 22 GB · ~151 tok/s
Other vendor
Qwen3.8 27B
Alibaba
- 56.6 higher Score
- 6.9 GB more VRAM
- 44 tok/s slower
Score 122.0 · 17.9 GB · ~38 tok/s
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | similar score |
| Gemma 4 31B ITGoogle | 106.7 | 21.7 GB | ~32 | similar score |
| Gemma 4 26B A4B ITGoogle | 105.8 | 16.5 GB | ~171 | similar score |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | similar score |
| Qwen3 30B A3B Thinking 2507Alibaba | 100.7 | 19.4 GB | ~173 | similar score |
| Qwen3.5 9BAlibaba | 99.4 | 6.6 GB | ~103 | similar score |
| Gemma 3 27B ITGoogle | 79.4 | 21.7 GB | ~36 | similar score |
| Gemma 2 27B ITGoogle | 72.7 | 19.5 GB | ~37 | similar score |
| Gemma 2 9B ITGoogle | 68.0 | 7.3 GB | ~107 | similar score |
| Qwen2.5 7B InstructAlibaba | 65.1 | 5.8 GB | ~131 | similar score |
Specifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 12.2B
- Architecture
- MistralForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2024-07-17
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Mistral Nemo Instruct 2407 need?
Mistral Nemo Instruct 2407 requires 8.1 GB of VRAM at Q4_K_M, or 25.2 GB at BF16. Full 131K context adds up to 26.4 GB (34.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 12.2B × 4.8 bits ÷ 8 = 7.3 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 27.2 GB (at full 131K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Mistral Nemo Instruct 2407?
Yes, at Q8_0 (13.0 GB) or lower. Higher quantizations like BF16 (25.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Mistral Nemo Instruct 2407?
For Mistral Nemo Instruct 2407, Q4_K_M (8.1 GB) offers the best balance of quality and VRAM usage. Q4_K_L (8.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 4.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Mistral Nemo Instruct 2407 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Mistral Nemo Instruct 2407. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 8.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Mistral Nemo Instruct 2407 locally?
Yes — Mistral Nemo Instruct 2407 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Mistral Nemo Instruct 2407?
At Q4_K_M, Mistral Nemo Instruct 2407 can reach ~595 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~81 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 8.07 × 0.65 = ~644 tok/s
Estimated speed at Q4_K_M (8.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Mistral Nemo Instruct 2407?
At Q4_K_M, the download is about 7.35 GB. The full-precision BF16 version is 24.50 GB. The smallest option (IQ2_XXS) is 3.37 GB.
Which GPUs can run Mistral Nemo Instruct 2407?
40 consumer GPUs can run Mistral Nemo Instruct 2407 at Q4_K_M. Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
Which devices can run Mistral Nemo Instruct 2407?
150 devices with unified memory can run Mistral Nemo Instruct 2407 at Q4_K_M (8.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.