Mistral 7B Instruct v0.2 vs Mistral Sk 7B
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Mistral 7B Instruct v0.2 | Mistral Sk 7B | |
|---|---|---|
| Parameters | 7.2B | 7B |
| Context | 33K | 33K |
| Architecture | MistralForCausalLM | MistralForCausalLM |
| License | Apache 2.0 | Apache 2.0 |
| Downloads | 2.2M | 2.1K |
| Released | Jul 2025 | Mar 2025 |
VRAM by Quantization: Mistral 7B Instruct v0.2 vs Mistral Sk 7B
| Quantization | Bits | Mistral 7B Instruct v0.2 VRAM | Mistral Sk 7B VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 3.6 GB | — |
| Q3_K_M | 3.90 | 4.1 GB | — |
| Q3_K_S | 3.50 | 3.7 GB | — |
| Q4_0 | 4.00 | 4.2 GB | — |
| Q4_K_M | 4.80 | 4.9 GB | — |
| Q5_K_M | 5.70 | 5.7 GB | — |
| Q6_K | 6.60 | 6.5 GB | — |
| Q8_0 | 8.00 | 7.8 GB | — |
Verdict
Mistral 7B Instruct v0.2 is the more widely downloaded of the two.
Frequently Asked Questions
- Which has a longer context window, Mistral 7B Instruct v0.2 or Mistral Sk 7B?
Mistral 7B Instruct v0.2 supports 32,768 tokens and Mistral Sk 7B supports 32,768 tokens.
- What is the difference between Mistral 7B Instruct v0.2 and Mistral Sk 7B?
Mistral 7B Instruct v0.2 is a 7.2B model from Mistral AI (Mistral family), while Mistral Sk 7B is a 7B model from slovak-nlp (Mistral family). Compare their VRAM requirements above to see which fits your GPU or Mac.